Upload TensorRT & ONNX Model files

.gitattributes

@@ -33,3 +33,35 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_l_fp16.onnx.best.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_l_fp16.onnx.fp16.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_l_fp32.onnx.best.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_l_fp32.onnx.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_l_fp32.onnx.fp16.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_l_fp32.onnx.int8.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_l_int8.onnx.best.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_l_int8.onnx.int8.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_m_fp16.onnx.best.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_m_fp16.onnx.fp16.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_m_fp32.onnx.best.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_m_fp32.onnx.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_m_fp32.onnx.fp16.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_m_fp32.onnx.int8.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_m_int8.onnx.best.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_m_int8.onnx.int8.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_n_fp16.onnx.best.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_n_fp16.onnx.fp16.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_n_fp32.onnx.best.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_n_fp32.onnx.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_n_fp32.onnx.fp16.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_n_fp32.onnx.int8.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_n_int8.onnx.best.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_n_int8.onnx.int8.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_s_fp16.onnx.best.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_s_fp16.onnx.fp16.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_s_fp32.onnx.best.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_s_fp32.onnx.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_s_fp32.onnx.fp16.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_s_fp32.onnx.int8.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_s_int8.onnx.best.engine filter=lfs diff=lfs merge=lfs -text
+yolo_nas_pose_s_int8.onnx.int8.engine filter=lfs diff=lfs merge=lfs -text

benchmark_with_trtexec.sh

@@ -0,0 +1,37 @@
+#!/bin/sh
+
+#/usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_n_fp32.onnx        --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_n_fp32.onnx.fp32.engine > yolo_nas_pose_n_fp32.onnx.fp32.engine.log 2> yolo_nas_pose_n_fp32.onnx.fp32.engine.err
+#/usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_n_fp32.onnx --fp16 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_n_fp32.onnx.fp16.engine > yolo_nas_pose_n_fp32.onnx.fp16.engine.log 2> yolo_nas_pose_n_fp32.onnx.fp16.engine.err
+#/usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_n_fp32.onnx --best --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_n_fp32.onnx.best.engine > yolo_nas_pose_n_fp32.onnx.best.engine.log 2> yolo_nas_pose_n_fp32.onnx.best.engine.err
+#/usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_n_fp32.onnx --int8 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_n_fp32.onnx.int8.engine > yolo_nas_pose_n_fp32.onnx.int8.engine.log 2> yolo_nas_pose_n_fp32.onnx.int8.engine.err
+#/usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_n_int8.onnx --int8 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_n_int8.onnx.int8.engine > yolo_nas_pose_n_int8.onnx.int8.engine.log 2> yolo_nas_pose_n_int8.onnx.int8.engine.err
+#/usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_s_fp32.onnx        --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_s_fp32.onnx.fp32.engine > yolo_nas_pose_s_fp32.onnx.fp32.engine.log 2> yolo_nas_pose_s_fp32.onnx.fp32.engine.err
+#/usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_s_fp32.onnx --fp16 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_s_fp32.onnx.fp16.engine > yolo_nas_pose_s_fp32.onnx.fp16.engine.log 2> yolo_nas_pose_s_fp32.onnx.fp16.engine.err
+#/usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_s_fp32.onnx --best --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_s_fp32.onnx.best.engine > yolo_nas_pose_s_fp32.onnx.best.engine.log 2> yolo_nas_pose_s_fp32.onnx.best.engine.err
+#/usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_s_fp32.onnx --int8 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_s_fp32.onnx.int8.engine > yolo_nas_pose_s_fp32.onnx.int8.engine.log 2> yolo_nas_pose_s_fp32.onnx.int8.engine.err
+#/usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_s_int8.onnx --int8 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_s_int8.onnx.int8.engine > yolo_nas_pose_s_int8.onnx.int8.engine.log 2> yolo_nas_pose_s_int8.onnx.int8.engine.err
+
+onnx_models=(
+    "yolo_nas_pose_n_fp32"
+    "yolo_nas_pose_n_fp16"
+    "yolo_nas_pose_n_int8"
+    "yolo_nas_pose_s_fp32"
+    "yolo_nas_pose_s_fp16"
+    "yolo_nas_pose_s_int8"
+    "yolo_nas_pose_m_fp32"
+    "yolo_nas_pose_m_fp16"
+    "yolo_nas_pose_m_int8"
+    "yolo_nas_pose_l_fp32"
+    "yolo_nas_pose_l_fp16"
+    "yolo_nas_pose_l_int8"
+)
+
+for onnx in "${onnx_models[@]}"; do
+    for opt in "" "--fp16" "--best" "--int8"; do
+        suffix=""
+        if [ ! -z "$opt" ]; then
+            suffix=".${opt:2}"
+        fi
+        /usr/src/tensorrt/bin/trtexec --onnx=${onnx}.onnx $opt --avgRuns=100 --duration=15 --saveEngine=${onnx}.onnx${suffix}.engine > ${onnx}.onnx${suffix}.engine.log 2> ${onnx}.onnx${suffix}.engine.err
+    done
+done

yolo_nas_pose_l_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4da0316c679b93931da1a30d1224d280991d2350354cb8df7338b0affc154e3
+size 108987993

yolo_nas_pose_l_fp16.onnx.best.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a88cce7911337fa5283e63dca004d66fef580a25ee5c322aad72f974c1259e3
+size 57159395

yolo_nas_pose_l_fp16.onnx.best.engine.err

@@ -0,0 +1,364 @@
+[12/28/2023-17:15:27] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-17:15:27] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-17:15:27] [W] [TRT] Calibrator is not being used. Users must provide dynamic range for all tensors that are not Int32 or Bool.
+[12/28/2023-17:48:46] [W] [TRT] Tactic Device request: 4720MB Available: 2777MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:48:46] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4720 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:48:47] [W] [TRT] Tactic Device request: 4720MB Available: 2777MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:48:47] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4720 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:48:47] [W] [TRT] Tactic Device request: 4720MB Available: 2777MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:48:47] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4720 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:48:52] [W] [TRT] Tactic Device request: 4706MB Available: 2784MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:48:53] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4706 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:48:53] [W] [TRT] Tactic Device request: 4706MB Available: 2784MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:48:53] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4706 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:48:57] [W] [TRT] Tactic Device request: 4711MB Available: 2755MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:48:57] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:48:58] [W] [TRT] Tactic Device request: 4711MB Available: 2755MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:48:58] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:48:59] [W] [TRT] Tactic Device request: 4711MB Available: 2755MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:48:59] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:49:04] [W] [TRT] Tactic Device request: 4702MB Available: 2754MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:49:04] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4702 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:49:04] [W] [TRT] Tactic Device request: 4702MB Available: 2755MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:49:04] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4702 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:49:08] [W] [TRT] Tactic Device request: 4711MB Available: 2711MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:49:08] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:49:09] [W] [TRT] Tactic Device request: 4711MB Available: 2711MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:49:09] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:49:09] [W] [TRT] Tactic Device request: 4711MB Available: 2711MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:49:10] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:49:15] [W] [TRT] Tactic Device request: 4702MB Available: 2710MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:49:15] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4702 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:49:15] [W] [TRT] Tactic Device request: 4702MB Available: 2710MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:49:15] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4702 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:56:52] [W] [TRT] Tactic Device request: 4711MB Available: 2405MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:56:52] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:56:52] [W] [TRT] Tactic Device request: 4711MB Available: 2407MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:56:52] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:56:52] [W] [TRT] Tactic Device request: 4711MB Available: 2407MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:56:52] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:56:54] [W] [TRT] Tactic Device request: 4701MB Available: 2406MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:56:54] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4701 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:56:54] [W] [TRT] Tactic Device request: 4701MB Available: 2407MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:56:54] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4701 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:57:13] [W] [TRT] Tactic Device request: 6275MB Available: 2406MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:57:13] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:57:13] [W] [TRT] Tactic Device request: 6275MB Available: 2406MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:57:13] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6275 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:57:13] [W] [TRT] Tactic Device request: 6275MB Available: 2406MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:57:13] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:57:15] [W] [TRT] Tactic Device request: 6270MB Available: 2405MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:57:15] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6270 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:57:15] [W] [TRT] Tactic Device request: 6270MB Available: 2405MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:57:15] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6270 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:08:00] [W] [TRT] Tactic Device request: 7056MB Available: 2739MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:08:00] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:08:01] [W] [TRT] Tactic Device request: 7056MB Available: 2738MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:08:01] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 7056 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:08:01] [W] [TRT] Tactic Device request: 7056MB Available: 2738MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:08:01] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:08:03] [W] [TRT] Tactic Device request: 7050MB Available: 2738MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:08:03] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7050 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:08:03] [W] [TRT] Tactic Device request: 7050MB Available: 2739MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:08:03] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 7050 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:08:23] [W] [TRT] Tactic Device request: 6354MB Available: 2732MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:08:24] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:08:24] [W] [TRT] Tactic Device request: 6354MB Available: 2731MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:08:24] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6354 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:08:24] [W] [TRT] Tactic Device request: 6354MB Available: 2732MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:08:24] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:08:26] [W] [TRT] Tactic Device request: 6351MB Available: 2732MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:08:26] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6351 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:08:26] [W] [TRT] Tactic Device request: 6351MB Available: 2732MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:08:26] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6351 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:23:59] [W] [TRT] Tactic Device request: 6540MB Available: 2641MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:23:59] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6540 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:23:59] [W] [TRT] Tactic Device request: 6540MB Available: 2641MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:23:59] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6540 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:23:59] [W] [TRT] Tactic Device request: 6540MB Available: 2641MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:23:59] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6540 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:24:01] [W] [TRT] Tactic Device request: 6538MB Available: 2642MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:24:01] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6538 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:24:01] [W] [TRT] Tactic Device request: 6538MB Available: 2641MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:24:01] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6538 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:32:34] [W] [TRT] Tactic Device request: 2457MB Available: 2443MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:32:34] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:32:34] [W] [TRT] Tactic Device request: 2457MB Available: 2444MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:32:34] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2457 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:32:34] [W] [TRT] Tactic Device request: 2457MB Available: 2444MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:32:34] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:32:35] [W] [TRT] Tactic Device request: 2456MB Available: 2444MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:32:35] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2456 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:32:35] [W] [TRT] Tactic Device request: 2456MB Available: 2444MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:32:35] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2456 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:33:03] [W] [TRT] Tactic Device request: 3587MB Available: 2405MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:33:03] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:33:03] [W] [TRT] Tactic Device request: 3587MB Available: 2405MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:33:03] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3587 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:33:03] [W] [TRT] Tactic Device request: 3587MB Available: 2405MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:33:03] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:33:04] [W] [TRT] Tactic Device request: 3585MB Available: 2405MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:33:04] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3585 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:33:04] [W] [TRT] Tactic Device request: 3585MB Available: 2405MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:33:04] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3585 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:45:49] [W] [TRT] Tactic Device request: 3556MB Available: 2253MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:45:49] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:45:49] [W] [TRT] Tactic Device request: 3556MB Available: 2254MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:45:49] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3556 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:45:49] [W] [TRT] Tactic Device request: 3556MB Available: 2254MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:45:49] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:45:50] [W] [TRT] Tactic Device request: 3551MB Available: 2254MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:45:50] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3551 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:45:50] [W] [TRT] Tactic Device request: 3551MB Available: 2254MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:45:50] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3551 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:45:52] [W] [TRT] Tactic Device request: 3140MB Available: 2253MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:45:52] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3140 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:45:52] [W] [TRT] Tactic Device request: 3140MB Available: 2253MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:45:52] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3140 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:45:52] [W] [TRT] Tactic Device request: 3140MB Available: 2253MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:45:52] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3140 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:45:53] [W] [TRT] Tactic Device request: 3136MB Available: 2253MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:45:53] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3136 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:45:53] [W] [TRT] Tactic Device request: 3136MB Available: 2253MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:45:53] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3136 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:57:51] [W] [TRT] Tactic Device request: 3161MB Available: 2021MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:57:51] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3161 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:57:51] [W] [TRT] Tactic Device request: 3161MB Available: 2021MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:57:51] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3161 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:57:51] [W] [TRT] Tactic Device request: 3161MB Available: 2021MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:57:51] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3161 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:57:52] [W] [TRT] Tactic Device request: 3156MB Available: 2021MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:57:52] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3156 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:57:52] [W] [TRT] Tactic Device request: 3156MB Available: 2021MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:57:52] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3156 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:57:59] [W] [TRT] Tactic Device request: 4189MB Available: 2022MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:57:59] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4189 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:57:59] [W] [TRT] Tactic Device request: 4189MB Available: 2015MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:57:59] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4189 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:58:00] [W] [TRT] Tactic Device request: 4189MB Available: 2016MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:58:00] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4189 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:58:04] [W] [TRT] Tactic Device request: 4183MB Available: 2018MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:58:04] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4183 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:58:04] [W] [TRT] Tactic Device request: 4183MB Available: 2017MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:58:04] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4183 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:58:08] [W] [TRT] Tactic Device request: 4186MB Available: 2017MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:58:08] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4186 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:58:08] [W] [TRT] Tactic Device request: 4186MB Available: 2015MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:58:08] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4186 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:58:09] [W] [TRT] Tactic Device request: 4186MB Available: 2016MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:58:09] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4186 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:58:13] [W] [TRT] Tactic Device request: 4182MB Available: 2016MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:58:13] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4182 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-18:58:13] [W] [TRT] Tactic Device request: 4182MB Available: 2015MB. Device memory is insufficient to use tactic.
+[12/28/2023-18:58:13] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4182 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:10:51] [W] [TRT] Tactic Device request: 4764MB Available: 1955MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:10:51] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4764 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:10:52] [W] [TRT] Tactic Device request: 4764MB Available: 1953MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:10:52] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4764 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:10:52] [W] [TRT] Tactic Device request: 4764MB Available: 1953MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:10:52] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4764 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:10:53] [W] [TRT] Tactic Device request: 4761MB Available: 1954MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:10:53] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4761 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:10:53] [W] [TRT] Tactic Device request: 4761MB Available: 1954MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:10:53] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4761 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:11:02] [W] [TRT] Tactic Device request: 4244MB Available: 1769MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:11:02] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4244 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:11:03] [W] [TRT] Tactic Device request: 4244MB Available: 1768MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:11:03] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4244 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:11:04] [W] [TRT] Tactic Device request: 4244MB Available: 1775MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:11:04] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4244 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:11:09] [W] [TRT] Tactic Device request: 4240MB Available: 1773MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:11:09] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4240 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:11:09] [W] [TRT] Tactic Device request: 4240MB Available: 1771MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:11:09] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4240 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:11:14] [W] [TRT] Tactic Device request: 4241MB Available: 1774MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:11:14] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4241 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:11:15] [W] [TRT] Tactic Device request: 4241MB Available: 1772MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:11:15] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4241 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:11:16] [W] [TRT] Tactic Device request: 4241MB Available: 1770MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:11:16] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4241 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:11:21] [W] [TRT] Tactic Device request: 4239MB Available: 1769MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:11:21] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4239 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:11:22] [W] [TRT] Tactic Device request: 4239MB Available: 1768MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:11:22] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4239 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:07] [W] [TRT] Tactic Device request: 1638MB Available: 1546MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:07] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 1638 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:07] [W] [TRT] Tactic Device request: 1638MB Available: 1546MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:07] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 1638 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:08] [W] [TRT] Tactic Device request: 1637MB Available: 1557MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:08] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 1637 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:08] [W] [TRT] Tactic Device request: 1637MB Available: 1557MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:08] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 1637 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:10] [W] [TRT] Tactic Device request: 3270MB Available: 1560MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:10] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3270 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:10] [W] [TRT] Tactic Device request: 3270MB Available: 1560MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:10] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3270 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:10] [W] [TRT] Tactic Device request: 3270MB Available: 1560MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:10] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3270 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:12] [W] [TRT] Tactic Device request: 3269MB Available: 1558MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:12] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3269 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:12] [W] [TRT] Tactic Device request: 3269MB Available: 1558MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:12] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3269 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:15] [W] [TRT] Tactic Device request: 4377MB Available: 1563MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:15] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4377 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:15] [W] [TRT] Tactic Device request: 2185MB Available: 1563MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:15] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2185 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:16] [W] [TRT] Tactic Device request: 4377MB Available: 1563MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:16] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4377 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:16] [W] [TRT] Tactic Device request: 2185MB Available: 1563MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:16] [W] [TRT] Skipping tactic 10 due to insufficient memory on requested size of 2185 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:16] [W] [TRT] Tactic Device request: 4377MB Available: 1561MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:16] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4377 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:16] [W] [TRT] Tactic Device request: 2185MB Available: 1561MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:16] [W] [TRT] Skipping tactic 16 due to insufficient memory on requested size of 2185 detected for tactic 0x0000000000000075.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:22] [W] [TRT] Tactic Device request: 4375MB Available: 1748MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:22] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4375 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:22] [W] [TRT] Tactic Device request: 2183MB Available: 1748MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:22] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2183 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:22] [W] [TRT] Tactic Device request: 4375MB Available: 1748MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:22] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4375 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:22] [W] [TRT] Tactic Device request: 2183MB Available: 1749MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:22] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2183 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:29] [W] [TRT] Tactic Device request: 4376MB Available: 1746MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:29] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4376 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:29] [W] [TRT] Tactic Device request: 2184MB Available: 1746MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:29] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2184 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:29] [W] [TRT] Tactic Device request: 4376MB Available: 1746MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:29] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4376 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:29] [W] [TRT] Tactic Device request: 2184MB Available: 1746MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:29] [W] [TRT] Skipping tactic 10 due to insufficient memory on requested size of 2184 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:30] [W] [TRT] Tactic Device request: 4376MB Available: 1746MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:30] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4376 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:30] [W] [TRT] Tactic Device request: 2184MB Available: 1746MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:30] [W] [TRT] Skipping tactic 16 due to insufficient memory on requested size of 2184 detected for tactic 0x0000000000000075.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:36] [W] [TRT] Tactic Device request: 4375MB Available: 1750MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:36] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4375 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:36] [W] [TRT] Tactic Device request: 2183MB Available: 1750MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:36] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2183 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:36] [W] [TRT] Tactic Device request: 4375MB Available: 1750MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:36] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4375 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:25:36] [W] [TRT] Tactic Device request: 2183MB Available: 1750MB. Device memory is insufficient to use tactic.
+[12/28/2023-19:25:36] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2183 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-19:26:56] [W] * Throughput may be bound by Enqueue Time rather than GPU Compute and the GPU may be under-utilized.
+[12/28/2023-19:26:56] [W]   If not already in use, --useCudaGraph (utilize CUDA graphs where possible) may increase the throughput.
+[12/28/2023-19:26:56] [W] * GPU compute time is unstable, with coefficient of variance = 6.77541%.
+[12/28/2023-19:26:56] [W]   If not already in use, locking GPU clock frequency or adding --useSpinWait may improve the stability.

yolo_nas_pose_l_fp16.onnx.best.engine.log

@@ -0,0 +1,331 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp16.onnx --best --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp16.onnx.best.engine
+[12/28/2023-17:15:16] [I] === Model Options ===
+[12/28/2023-17:15:16] [I] Format: ONNX
+[12/28/2023-17:15:16] [I] Model: yolo_nas_pose_l_fp16.onnx
+[12/28/2023-17:15:16] [I] Output:
+[12/28/2023-17:15:16] [I] === Build Options ===
+[12/28/2023-17:15:16] [I] Max batch: explicit batch
+[12/28/2023-17:15:16] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-17:15:16] [I] minTiming: 1
+[12/28/2023-17:15:16] [I] avgTiming: 8
+[12/28/2023-17:15:16] [I] Precision: FP32+FP16+INT8
+[12/28/2023-17:15:16] [I] LayerPrecisions: 
+[12/28/2023-17:15:16] [I] Calibration: Dynamic
+[12/28/2023-17:15:16] [I] Refit: Disabled
+[12/28/2023-17:15:16] [I] Sparsity: Disabled
+[12/28/2023-17:15:16] [I] Safe mode: Disabled
+[12/28/2023-17:15:16] [I] DirectIO mode: Disabled
+[12/28/2023-17:15:16] [I] Restricted mode: Disabled
+[12/28/2023-17:15:16] [I] Build only: Disabled
+[12/28/2023-17:15:16] [I] Save engine: yolo_nas_pose_l_fp16.onnx.best.engine
+[12/28/2023-17:15:16] [I] Load engine: 
+[12/28/2023-17:15:16] [I] Profiling verbosity: 0
+[12/28/2023-17:15:16] [I] Tactic sources: Using default tactic sources
+[12/28/2023-17:15:16] [I] timingCacheMode: local
+[12/28/2023-17:15:16] [I] timingCacheFile: 
+[12/28/2023-17:15:16] [I] Heuristic: Disabled
+[12/28/2023-17:15:16] [I] Preview Features: Use default preview flags.
+[12/28/2023-17:15:16] [I] Input(s)s format: fp32:CHW
+[12/28/2023-17:15:16] [I] Output(s)s format: fp32:CHW
+[12/28/2023-17:15:16] [I] Input build shapes: model
+[12/28/2023-17:15:16] [I] Input calibration shapes: model
+[12/28/2023-17:15:16] [I] === System Options ===
+[12/28/2023-17:15:16] [I] Device: 0
+[12/28/2023-17:15:16] [I] DLACore: 
+[12/28/2023-17:15:16] [I] Plugins:
+[12/28/2023-17:15:16] [I] === Inference Options ===
+[12/28/2023-17:15:16] [I] Batch: Explicit
+[12/28/2023-17:15:16] [I] Input inference shapes: model
+[12/28/2023-17:15:16] [I] Iterations: 10
+[12/28/2023-17:15:16] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-17:15:16] [I] Sleep time: 0ms
+[12/28/2023-17:15:16] [I] Idle time: 0ms
+[12/28/2023-17:15:16] [I] Streams: 1
+[12/28/2023-17:15:16] [I] ExposeDMA: Disabled
+[12/28/2023-17:15:16] [I] Data transfers: Enabled
+[12/28/2023-17:15:16] [I] Spin-wait: Disabled
+[12/28/2023-17:15:16] [I] Multithreading: Disabled
+[12/28/2023-17:15:16] [I] CUDA Graph: Disabled
+[12/28/2023-17:15:16] [I] Separate profiling: Disabled
+[12/28/2023-17:15:16] [I] Time Deserialize: Disabled
+[12/28/2023-17:15:16] [I] Time Refit: Disabled
+[12/28/2023-17:15:16] [I] NVTX verbosity: 0
+[12/28/2023-17:15:16] [I] Persistent Cache Ratio: 0
+[12/28/2023-17:15:16] [I] Inputs:
+[12/28/2023-17:15:16] [I] === Reporting Options ===
+[12/28/2023-17:15:16] [I] Verbose: Disabled
+[12/28/2023-17:15:16] [I] Averages: 100 inferences
+[12/28/2023-17:15:16] [I] Percentiles: 90,95,99
+[12/28/2023-17:15:16] [I] Dump refittable layers:Disabled
+[12/28/2023-17:15:16] [I] Dump output: Disabled
+[12/28/2023-17:15:16] [I] Profile: Disabled
+[12/28/2023-17:15:16] [I] Export timing to JSON file: 
+[12/28/2023-17:15:16] [I] Export output to JSON file: 
+[12/28/2023-17:15:16] [I] Export profile to JSON file: 
+[12/28/2023-17:15:16] [I] 
+[12/28/2023-17:15:16] [I] === Device Information ===
+[12/28/2023-17:15:16] [I] Selected Device: Orin
+[12/28/2023-17:15:16] [I] Compute Capability: 8.7
+[12/28/2023-17:15:16] [I] SMs: 8
+[12/28/2023-17:15:16] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-17:15:16] [I] Device Global Memory: 7471 MiB
+[12/28/2023-17:15:16] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-17:15:16] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-17:15:16] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-17:15:16] [I] 
+[12/28/2023-17:15:16] [I] TensorRT version: 8.5.2
+[12/28/2023-17:15:21] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 2974 (MiB)
+[12/28/2023-17:15:25] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +286, now: CPU 574, GPU 3278 (MiB)
+[12/28/2023-17:15:25] [I] Start parsing network model
+[12/28/2023-17:15:27] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-17:15:27] [I] [TRT] Input filename:   yolo_nas_pose_l_fp16.onnx
+[12/28/2023-17:15:27] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-17:15:27] [I] [TRT] Opset version:    17
+[12/28/2023-17:15:27] [I] [TRT] Producer name:    pytorch
+[12/28/2023-17:15:27] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-17:15:27] [I] [TRT] Domain:           
+[12/28/2023-17:15:27] [I] [TRT] Model version:    0
+[12/28/2023-17:15:27] [I] [TRT] Doc string:       
+[12/28/2023-17:15:27] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-17:15:27] [I] Finish parsing network model
+[12/28/2023-17:15:28] [I] [TRT] ---------- Layers Running on DLA ----------
+[12/28/2023-17:15:28] [I] [TRT] ---------- Layers Running on GPU ----------
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation1]
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/pre_process/pre_process.0/Cast.../pre_process/pre_process.2/Mul]}
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 458) [Constant]
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 459) [Constant]
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 460) [Constant]
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stem/conv/rbr_reparam/Conv + /model/backbone/stem/conv/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/downsample/rbr_reparam/Conv + /model/backbone/stage1/downsample/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv2/conv/Conv + /model/backbone/stage1/blocks/conv2/act/Relu || /model/backbone/stage1/blocks/conv1/conv/Conv + /model/backbone/stage1/blocks/conv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 15) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 23) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv3/conv/Conv + /model/backbone/stage1/blocks/conv3/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_skip2/conv/Conv + /model/neck/neck2/reduce_skip2/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/downsample/rbr_reparam/Conv + /model/backbone/stage2/downsample/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/downsample/conv/Conv + /model/neck/neck2/downsample/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv2/conv/Conv + /model/backbone/stage2/blocks/conv2/act/Relu || /model/backbone/stage2/blocks/conv1/conv/Conv + /model/backbone/stage2/blocks/conv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 44) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 52) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 60) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv3/conv/Conv + /model/backbone/stage2/blocks/conv3/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip2/conv/Conv + /model/neck/neck1/reduce_skip2/act/Relu || /model/neck/neck2/reduce_skip1/conv/Conv + /model/neck/neck2/reduce_skip1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/downsample/rbr_reparam/Conv + /model/backbone/stage3/downsample/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/downsample/conv/Conv + /model/neck/neck1/downsample/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv2/conv/Conv + /model/backbone/stage3/blocks/conv2/act/Relu || /model/backbone/stage3/blocks/conv1/conv/Conv + /model/backbone/stage3/blocks/conv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 83) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 91) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 99) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 107) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.4.alpha + (Unnamed Layer* 115) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv3/conv/Conv + /model/backbone/stage3/blocks/conv3/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip1/conv/Conv + /model/neck/neck1/reduce_skip1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/downsample/rbr_reparam/Conv + /model/backbone/stage4/downsample/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv2/conv/Conv + /model/backbone/stage4/blocks/conv2/act/Relu || /model/backbone/stage4/blocks/conv1/conv/Conv + /model/backbone/stage4/blocks/conv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 134) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 142) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv3/conv/Conv + /model/backbone/stage4/blocks/conv3/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv1/conv/Conv + /model/backbone/context_module/cv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.2/MaxPool
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.1/MaxPool
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.0/MaxPool
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/backbone/context_module/cv1/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv2/conv/Conv + /model/backbone/context_module/cv2/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/conv/conv/Conv + /model/neck/neck1/conv/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck1/upsample/ConvTranspose
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_after_concat/conv/Conv + /model/neck/neck1/reduce_after_concat/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv2/conv/Conv + /model/neck/neck1/blocks/conv2/act/Relu || /model/neck/neck1/blocks/conv1/conv/Conv + /model/neck/neck1/blocks/conv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 171) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 179) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.2.alpha + (Unnamed Layer* 187) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.3.alpha + (Unnamed Layer* 195) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv3/conv/Conv + /model/neck/neck1/blocks/conv3/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/conv/conv/Conv + /model/neck/neck2/conv/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck2/upsample/ConvTranspose
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/reduce_skip1/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_after_concat/conv/Conv + /model/neck/neck2/reduce_after_concat/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv2/conv/Conv + /model/neck/neck2/blocks/conv2/act/Relu || /model/neck/neck2/blocks/conv1/conv/Conv + /model/neck/neck2/blocks/conv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 216) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 224) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 232) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.3.alpha + (Unnamed Layer* 240) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv3/conv/Conv + /model/neck/neck2/blocks/conv3/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/bbox_stem/seq/conv/Conv + /model/heads/head1/bbox_stem/seq/act/Relu || /model/heads/head1/pose_stem/seq/conv/Conv + /model/heads/head1/pose_stem/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/conv/conv/Conv + /model/neck/neck3/conv/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head1/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head1/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head1/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv2/conv/Conv + /model/neck/neck3/blocks/conv2/act/Relu || /model/neck/neck3/blocks/conv1/conv/Conv + /model/neck/neck3/blocks/conv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/cls_pred/Conv
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_pred/Conv
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape + /model/heads/Transpose
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_pred/Conv
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 271) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 294) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 302) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 310) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv3/conv/Conv + /model/neck/neck3/blocks/conv3/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_stem/seq/conv/Conv + /model/heads/head2/pose_stem/seq/act/Relu || /model/heads/head2/bbox_stem/seq/conv/Conv + /model/heads/head2/bbox_stem/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/conv/conv/Conv + /model/neck/neck4/conv/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head2/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head2/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head2/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv2/conv/Conv + /model/neck/neck4/blocks/conv2/act/Relu || /model/neck/neck4/blocks/conv1/conv/Conv + /model/neck/neck4/blocks/conv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/cls_pred/Conv
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_pred/Conv
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_4 + /model/heads/Transpose_3
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_pred/Conv
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_1
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 341) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_1
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 364) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.2.alpha + (Unnamed Layer* 372) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.3.alpha + (Unnamed Layer* 380) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv3/conv/Conv + /model/neck/neck4/blocks/conv3/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/bbox_stem/seq/conv/Conv + /model/heads/head3/bbox_stem/seq/act/Relu || /model/heads/head3/pose_stem/seq/conv/Conv + /model/heads/head3/pose_stem/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head3/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head3/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head3/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/cls_pred/Conv
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_pred/Conv
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_8 + /model/heads/Transpose_6
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.2/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.2/seq/act/Relu
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_2
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_pred/Conv
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_2
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice_1...cast_boxes_to_fp32]}
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] NMS: batched_nms_26
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] DEVICE_TO_SHAPE_HOST: (Unnamed Layer* 462) [NMS]_1_output[DevicetoShapeHostCopy]
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation2]
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice...graph2_/Concat_5]}
+[12/28/2023-17:15:28] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation3]
+[12/28/2023-17:15:40] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +534, GPU +308, now: CPU 1231, GPU 3787 (MiB)
+[12/28/2023-17:15:42] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +83, GPU +72, now: CPU 1314, GPU 3859 (MiB)
+[12/28/2023-17:15:42] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
+[12/28/2023-19:26:12] [I] [TRT] Total Activation Memory: 7966500352
+[12/28/2023-19:26:12] [I] [TRT] Detected 1 inputs and 1 output network tensors.
+[12/28/2023-19:26:29] [I] [TRT] Total Host Persistent Memory: 330912
+[12/28/2023-19:26:29] [I] [TRT] Total Device Persistent Memory: 656384
+[12/28/2023-19:26:29] [I] [TRT] Total Scratch Memory: 134217728
+[12/28/2023-19:26:29] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 79 MiB, GPU 2398 MiB
+[12/28/2023-19:26:29] [I] [TRT] [BlockAssignment] Started assigning block shifts. This will take 176 steps to complete.
+[12/28/2023-19:26:29] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 96.1396ms to assign 14 blocks to 176 nodes requiring 149010944 bytes.
+[12/28/2023-19:26:29] [I] [TRT] Total Activation Memory: 149010944
+[12/28/2023-19:26:38] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU -17, now: CPU 1718, GPU 5578 (MiB)
+[12/28/2023-19:26:38] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +52, GPU +64, now: CPU 52, GPU 64 (MiB)
+[12/28/2023-19:26:39] [I] Engine built in 7882.87 sec.
+[12/28/2023-19:26:40] [I] [TRT] Loaded engine size: 54 MiB
+[12/28/2023-19:26:41] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1299, GPU 5193 (MiB)
+[12/28/2023-19:26:41] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +52, now: CPU 0, GPU 52 (MiB)
+[12/28/2023-19:26:41] [I] Engine deserialized in 0.300217 sec.
+[12/28/2023-19:26:41] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1300, GPU 5193 (MiB)
+[12/28/2023-19:26:41] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +143, now: CPU 0, GPU 195 (MiB)
+[12/28/2023-19:26:41] [I] Setting persistentCacheLimit to 0 bytes.
+[12/28/2023-19:26:41] [I] Using random values for input onnx::Cast_0
+[12/28/2023-19:26:41] [I] Created input binding for onnx::Cast_0 with dimensions 1x3x640x640
+[12/28/2023-19:26:41] [I] Using random values for output graph2_flat_predictions
+[12/28/2023-19:26:41] [I] Created output binding for graph2_flat_predictions with dimensions -1x57
+[12/28/2023-19:26:41] [I] Starting inference
+[12/28/2023-19:26:56] [I] Warmup completed 6 queries over 200 ms
+[12/28/2023-19:26:56] [I] Timing trace has 703 queries over 15.0461 s
+[12/28/2023-19:26:56] [I] 
+[12/28/2023-19:26:56] [I] === Trace details ===
+[12/28/2023-19:26:56] [I] Trace averages of 100 runs:
+[12/28/2023-19:26:56] [I] Average on 100 runs - GPU latency: 20.9395 ms - Host latency: 21.0535 ms (enqueue 21.0062 ms)
+[12/28/2023-19:26:56] [I] Average on 100 runs - GPU latency: 21.1664 ms - Host latency: 21.2792 ms (enqueue 21.2275 ms)
+[12/28/2023-19:26:56] [I] Average on 100 runs - GPU latency: 21.3262 ms - Host latency: 21.4444 ms (enqueue 21.3939 ms)
+[12/28/2023-19:26:56] [I] Average on 100 runs - GPU latency: 21.3667 ms - Host latency: 21.4831 ms (enqueue 21.4306 ms)
+[12/28/2023-19:26:56] [I] Average on 100 runs - GPU latency: 21.2193 ms - Host latency: 21.3339 ms (enqueue 21.2934 ms)
+[12/28/2023-19:26:56] [I] Average on 100 runs - GPU latency: 21.8831 ms - Host latency: 22.0036 ms (enqueue 21.9394 ms)
+[12/28/2023-19:26:56] [I] Average on 100 runs - GPU latency: 20.8839 ms - Host latency: 20.9973 ms (enqueue 20.9568 ms)
+[12/28/2023-19:26:56] [I] 
+[12/28/2023-19:26:56] [I] === Performance summary ===
+[12/28/2023-19:26:56] [I] Throughput: 46.7231 qps
+[12/28/2023-19:26:56] [I] Latency: min = 19.8525 ms, max = 30.6865 ms, mean = 21.368 ms, median = 21.1562 ms, percentile(90%) = 22.2715 ms, percentile(95%) = 23.1201 ms, percentile(99%) = 28.8721 ms
+[12/28/2023-19:26:56] [I] Enqueue Time: min = 19.8208 ms, max = 30.626 ms, mean = 21.3184 ms, median = 21.1201 ms, percentile(90%) = 22.2363 ms, percentile(95%) = 23.2373 ms, percentile(99%) = 28.8086 ms
+[12/28/2023-19:26:56] [I] H2D Latency: min = 0.0810547 ms, max = 0.134766 ms, mean = 0.0972954 ms, median = 0.0981445 ms, percentile(90%) = 0.100098 ms, percentile(95%) = 0.100586 ms, percentile(99%) = 0.111328 ms
+[12/28/2023-19:26:56] [I] GPU Compute Time: min = 19.7407 ms, max = 30.5723 ms, mean = 21.2522 ms, median = 21.042 ms, percentile(90%) = 22.1533 ms, percentile(95%) = 23.0203 ms, percentile(99%) = 28.7578 ms
+[12/28/2023-19:26:56] [I] D2H Latency: min = 0.00390625 ms, max = 0.0776367 ms, mean = 0.0184049 ms, median = 0.0155029 ms, percentile(90%) = 0.0283203 ms, percentile(95%) = 0.0302734 ms, percentile(99%) = 0.046875 ms
+[12/28/2023-19:26:56] [I] Total Host Walltime: 15.0461 s
+[12/28/2023-19:26:56] [I] Total GPU Compute Time: 14.9403 s
+[12/28/2023-19:26:56] [I] Explanations of the performance metrics are printed in the verbose logs.
+[12/28/2023-19:26:56] [I] 
+&&&& PASSED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp16.onnx --best --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp16.onnx.best.engine

yolo_nas_pose_l_fp16.onnx.engine.err

@@ -0,0 +1,8 @@
+[12/28/2023-16:09:44] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-16:09:44] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-16:09:45] [E] Error[4]: [network.cpp::validate::2925] Error Code 4: Internal Error (fp16 precision has been set for a layer or layer output, but fp16 is not configured in the builder)
+[12/28/2023-16:09:45] [E] Error[2]: [builder.cpp::buildSerializedNetwork::751] Error Code 2: Internal Error (Assertion engine != nullptr failed. )
+[12/28/2023-16:09:45] [E] Engine could not be created from network
+[12/28/2023-16:09:45] [E] Building engine failed
+[12/28/2023-16:09:45] [E] Failed to create engine from model or file.
+[12/28/2023-16:09:45] [E] Engine set up failed

yolo_nas_pose_l_fp16.onnx.engine.log

@@ -0,0 +1,91 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp16.onnx --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp16.onnx.engine
+[12/28/2023-16:09:34] [I] === Model Options ===
+[12/28/2023-16:09:34] [I] Format: ONNX
+[12/28/2023-16:09:34] [I] Model: yolo_nas_pose_l_fp16.onnx
+[12/28/2023-16:09:34] [I] Output:
+[12/28/2023-16:09:34] [I] === Build Options ===
+[12/28/2023-16:09:34] [I] Max batch: explicit batch
+[12/28/2023-16:09:34] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-16:09:34] [I] minTiming: 1
+[12/28/2023-16:09:34] [I] avgTiming: 8
+[12/28/2023-16:09:34] [I] Precision: FP32
+[12/28/2023-16:09:34] [I] LayerPrecisions: 
+[12/28/2023-16:09:34] [I] Calibration: 
+[12/28/2023-16:09:34] [I] Refit: Disabled
+[12/28/2023-16:09:34] [I] Sparsity: Disabled
+[12/28/2023-16:09:34] [I] Safe mode: Disabled
+[12/28/2023-16:09:34] [I] DirectIO mode: Disabled
+[12/28/2023-16:09:34] [I] Restricted mode: Disabled
+[12/28/2023-16:09:34] [I] Build only: Disabled
+[12/28/2023-16:09:34] [I] Save engine: yolo_nas_pose_l_fp16.onnx.engine
+[12/28/2023-16:09:34] [I] Load engine: 
+[12/28/2023-16:09:34] [I] Profiling verbosity: 0
+[12/28/2023-16:09:34] [I] Tactic sources: Using default tactic sources
+[12/28/2023-16:09:34] [I] timingCacheMode: local
+[12/28/2023-16:09:34] [I] timingCacheFile: 
+[12/28/2023-16:09:34] [I] Heuristic: Disabled
+[12/28/2023-16:09:34] [I] Preview Features: Use default preview flags.
+[12/28/2023-16:09:34] [I] Input(s)s format: fp32:CHW
+[12/28/2023-16:09:34] [I] Output(s)s format: fp32:CHW
+[12/28/2023-16:09:34] [I] Input build shapes: model
+[12/28/2023-16:09:34] [I] Input calibration shapes: model
+[12/28/2023-16:09:34] [I] === System Options ===
+[12/28/2023-16:09:34] [I] Device: 0
+[12/28/2023-16:09:34] [I] DLACore: 
+[12/28/2023-16:09:34] [I] Plugins:
+[12/28/2023-16:09:34] [I] === Inference Options ===
+[12/28/2023-16:09:34] [I] Batch: Explicit
+[12/28/2023-16:09:34] [I] Input inference shapes: model
+[12/28/2023-16:09:34] [I] Iterations: 10
+[12/28/2023-16:09:34] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-16:09:34] [I] Sleep time: 0ms
+[12/28/2023-16:09:34] [I] Idle time: 0ms
+[12/28/2023-16:09:34] [I] Streams: 1
+[12/28/2023-16:09:34] [I] ExposeDMA: Disabled
+[12/28/2023-16:09:34] [I] Data transfers: Enabled
+[12/28/2023-16:09:34] [I] Spin-wait: Disabled
+[12/28/2023-16:09:34] [I] Multithreading: Disabled
+[12/28/2023-16:09:34] [I] CUDA Graph: Disabled
+[12/28/2023-16:09:34] [I] Separate profiling: Disabled
+[12/28/2023-16:09:34] [I] Time Deserialize: Disabled
+[12/28/2023-16:09:34] [I] Time Refit: Disabled
+[12/28/2023-16:09:34] [I] NVTX verbosity: 0
+[12/28/2023-16:09:34] [I] Persistent Cache Ratio: 0
+[12/28/2023-16:09:34] [I] Inputs:
+[12/28/2023-16:09:34] [I] === Reporting Options ===
+[12/28/2023-16:09:34] [I] Verbose: Disabled
+[12/28/2023-16:09:34] [I] Averages: 100 inferences
+[12/28/2023-16:09:34] [I] Percentiles: 90,95,99
+[12/28/2023-16:09:34] [I] Dump refittable layers:Disabled
+[12/28/2023-16:09:34] [I] Dump output: Disabled
+[12/28/2023-16:09:34] [I] Profile: Disabled
+[12/28/2023-16:09:34] [I] Export timing to JSON file: 
+[12/28/2023-16:09:34] [I] Export output to JSON file: 
+[12/28/2023-16:09:34] [I] Export profile to JSON file: 
+[12/28/2023-16:09:34] [I] 
+[12/28/2023-16:09:34] [I] === Device Information ===
+[12/28/2023-16:09:34] [I] Selected Device: Orin
+[12/28/2023-16:09:34] [I] Compute Capability: 8.7
+[12/28/2023-16:09:34] [I] SMs: 8
+[12/28/2023-16:09:34] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-16:09:34] [I] Device Global Memory: 7471 MiB
+[12/28/2023-16:09:34] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-16:09:34] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-16:09:34] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-16:09:34] [I] 
+[12/28/2023-16:09:34] [I] TensorRT version: 8.5.2
+[12/28/2023-16:09:39] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 2974 (MiB)
+[12/28/2023-16:09:43] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +283, now: CPU 574, GPU 3281 (MiB)
+[12/28/2023-16:09:43] [I] Start parsing network model
+[12/28/2023-16:09:44] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-16:09:44] [I] [TRT] Input filename:   yolo_nas_pose_l_fp16.onnx
+[12/28/2023-16:09:44] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-16:09:44] [I] [TRT] Opset version:    17
+[12/28/2023-16:09:44] [I] [TRT] Producer name:    pytorch
+[12/28/2023-16:09:44] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-16:09:44] [I] [TRT] Domain:           
+[12/28/2023-16:09:44] [I] [TRT] Model version:    0
+[12/28/2023-16:09:44] [I] [TRT] Doc string:       
+[12/28/2023-16:09:44] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-16:09:45] [I] Finish parsing network model
+&&&& FAILED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp16.onnx --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp16.onnx.engine

yolo_nas_pose_l_fp16.onnx.fp16.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:467ff31eefb68768b955df2011c89f375ab57c09a32840d671def8b3ad75de34
+size 110752021

yolo_nas_pose_l_fp16.onnx.fp16.engine.err

@@ -0,0 +1,423 @@
+[12/28/2023-16:09:49] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-16:09:49] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-16:15:22] [W] [TRT] Tactic Device request: 4720MB Available: 3156MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:15:22] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4720 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:15:23] [W] [TRT] Tactic Device request: 4720MB Available: 3155MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:15:23] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4720 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:15:23] [W] [TRT] Tactic Device request: 4720MB Available: 3155MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:15:23] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4720 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:15:29] [W] [TRT] Tactic Device request: 4706MB Available: 3154MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:15:29] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4706 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:15:29] [W] [TRT] Tactic Device request: 4706MB Available: 3155MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:15:29] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4706 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:15:32] [W] [TRT] Tactic Device request: 4711MB Available: 3148MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:15:32] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:15:32] [W] [TRT] Tactic Device request: 4711MB Available: 3147MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:15:32] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:15:33] [W] [TRT] Tactic Device request: 4711MB Available: 3146MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:15:33] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:15:38] [W] [TRT] Tactic Device request: 4702MB Available: 3147MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:15:38] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4702 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:15:38] [W] [TRT] Tactic Device request: 4702MB Available: 3147MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:15:39] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4702 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:20:16] [W] [TRT] Tactic Device request: 4711MB Available: 3039MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:20:16] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:20:16] [W] [TRT] Tactic Device request: 4711MB Available: 3039MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:20:16] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:20:16] [W] [TRT] Tactic Device request: 4711MB Available: 3038MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:20:16] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:20:18] [W] [TRT] Tactic Device request: 4701MB Available: 3039MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:20:18] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4701 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:20:18] [W] [TRT] Tactic Device request: 4701MB Available: 3039MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:20:18] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4701 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:20:33] [W] [TRT] Tactic Device request: 6275MB Available: 3038MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:20:33] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:20:33] [W] [TRT] Tactic Device request: 6275MB Available: 3039MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:20:33] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6275 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:20:33] [W] [TRT] Tactic Device request: 6275MB Available: 3038MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:20:33] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:20:35] [W] [TRT] Tactic Device request: 6270MB Available: 3039MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:20:35] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6270 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:20:35] [W] [TRT] Tactic Device request: 6270MB Available: 3039MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:20:35] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6270 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:27:09] [W] [TRT] Tactic Device request: 7056MB Available: 2339MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:27:09] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:27:09] [W] [TRT] Tactic Device request: 7056MB Available: 2340MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:27:09] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 7056 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:27:09] [W] [TRT] Tactic Device request: 7056MB Available: 2340MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:27:09] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:27:11] [W] [TRT] Tactic Device request: 7050MB Available: 2338MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:27:11] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7050 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:27:11] [W] [TRT] Tactic Device request: 7050MB Available: 2338MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:27:11] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 7050 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:27:27] [W] [TRT] Tactic Device request: 6354MB Available: 2340MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:27:27] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:27:27] [W] [TRT] Tactic Device request: 6354MB Available: 2338MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:27:28] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6354 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:27:28] [W] [TRT] Tactic Device request: 6354MB Available: 2339MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:27:28] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:27:29] [W] [TRT] Tactic Device request: 6351MB Available: 2341MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:27:29] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6351 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:27:29] [W] [TRT] Tactic Device request: 6351MB Available: 2341MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:27:29] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6351 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:16] [W] [TRT] Tactic Device request: 2394MB Available: 2304MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:16] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2394 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:16] [W] [TRT] Tactic Device request: 2394MB Available: 2304MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:16] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2394 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:16] [W] [TRT] Tactic Device request: 2394MB Available: 2304MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:16] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2394 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:17] [W] [TRT] Tactic Device request: 2392MB Available: 2304MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:17] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:17] [W] [TRT] Tactic Device request: 2392MB Available: 2304MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:17] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2392 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:17] [W] [TRT] Tactic Device request: 2392MB Available: 2304MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:17] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:18] [W] [TRT] Tactic Device request: 2391MB Available: 2305MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:18] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2391 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:18] [W] [TRT] Tactic Device request: 2391MB Available: 2305MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:18] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2391 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:18] [W] [TRT] Tactic Device request: 2390MB Available: 2305MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:18] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2390 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:18] [W] [TRT] Tactic Device request: 2390MB Available: 2305MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:18] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2390 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:32] [W] [TRT] Tactic Device request: 6540MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:32] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6540 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:32] [W] [TRT] Tactic Device request: 6540MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:32] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6540 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:33] [W] [TRT] Tactic Device request: 6540MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:33] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6540 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:34] [W] [TRT] Tactic Device request: 6538MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:34] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6538 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:35] [W] [TRT] Tactic Device request: 6538MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:35] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6538 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:36] [W] [TRT] Tactic Device request: 2191MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:36] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2191 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:37] [W] [TRT] Tactic Device request: 2191MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:37] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2191 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:38] [W] [TRT] Tactic Device request: 2191MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:38] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2191 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:42] [W] [TRT] Tactic Device request: 2190MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:42] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:43] [W] [TRT] Tactic Device request: 2190MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:43] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:45] [W] [TRT] Tactic Device request: 2190MB Available: 2130MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:45] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:46] [W] [TRT] Tactic Device request: 2190MB Available: 2129MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:46] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:47] [W] [TRT] Tactic Device request: 2190MB Available: 2127MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:47] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:51] [W] [TRT] Tactic Device request: 2190MB Available: 2127MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:51] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:36:52] [W] [TRT] Tactic Device request: 2190MB Available: 2126MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:36:52] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:41:41] [W] [TRT] Tactic Device request: 2457MB Available: 2417MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:41:41] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:41:42] [W] [TRT] Tactic Device request: 2457MB Available: 2417MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:41:42] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2457 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:41:42] [W] [TRT] Tactic Device request: 2457MB Available: 2417MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:41:42] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:41:43] [W] [TRT] Tactic Device request: 2456MB Available: 2418MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:41:43] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2456 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:41:43] [W] [TRT] Tactic Device request: 2456MB Available: 2418MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:41:43] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2456 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:42:04] [W] [TRT] Tactic Device request: 3587MB Available: 2216MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:42:04] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:42:04] [W] [TRT] Tactic Device request: 3587MB Available: 2216MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:42:04] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3587 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:42:04] [W] [TRT] Tactic Device request: 3587MB Available: 2217MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:42:04] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:42:06] [W] [TRT] Tactic Device request: 3585MB Available: 2233MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:42:06] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3585 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:42:06] [W] [TRT] Tactic Device request: 3585MB Available: 2233MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:42:06] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3585 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:49:44] [W] [TRT] Tactic Device request: 3556MB Available: 1928MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:49:44] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:49:44] [W] [TRT] Tactic Device request: 3556MB Available: 1928MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:49:44] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3556 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:49:44] [W] [TRT] Tactic Device request: 3556MB Available: 1928MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:49:44] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:49:45] [W] [TRT] Tactic Device request: 3551MB Available: 1929MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:49:45] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3551 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:49:45] [W] [TRT] Tactic Device request: 3551MB Available: 1929MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:49:45] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3551 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:49:46] [W] [TRT] Tactic Device request: 3140MB Available: 1930MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:49:46] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3140 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:49:46] [W] [TRT] Tactic Device request: 3140MB Available: 1929MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:49:46] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3140 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:49:46] [W] [TRT] Tactic Device request: 3140MB Available: 1929MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:49:46] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3140 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:49:47] [W] [TRT] Tactic Device request: 3136MB Available: 1929MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:49:48] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3136 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:49:48] [W] [TRT] Tactic Device request: 3136MB Available: 1929MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:49:48] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3136 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:56:57] [W] [TRT] Tactic Device request: 3161MB Available: 2194MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:56:57] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3161 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:56:57] [W] [TRT] Tactic Device request: 3161MB Available: 2194MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:56:57] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3161 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:56:57] [W] [TRT] Tactic Device request: 3161MB Available: 2194MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:56:57] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3161 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:56:58] [W] [TRT] Tactic Device request: 3156MB Available: 2195MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:56:58] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3156 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:56:58] [W] [TRT] Tactic Device request: 3156MB Available: 2195MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:56:58] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3156 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:57:03] [W] [TRT] Tactic Device request: 4189MB Available: 2194MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:57:03] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4189 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:57:03] [W] [TRT] Tactic Device request: 4189MB Available: 2194MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:57:03] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4189 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:57:04] [W] [TRT] Tactic Device request: 4189MB Available: 2193MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:57:04] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4189 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:57:08] [W] [TRT] Tactic Device request: 4183MB Available: 2193MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:57:08] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4183 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:57:08] [W] [TRT] Tactic Device request: 4183MB Available: 2193MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:57:08] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4183 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:57:10] [W] [TRT] Tactic Device request: 4186MB Available: 2194MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:57:10] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4186 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:57:11] [W] [TRT] Tactic Device request: 4186MB Available: 2194MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:57:11] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4186 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:57:11] [W] [TRT] Tactic Device request: 4186MB Available: 2194MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:57:11] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4186 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:57:15] [W] [TRT] Tactic Device request: 4182MB Available: 2193MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:57:15] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4182 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:57:16] [W] [TRT] Tactic Device request: 4182MB Available: 2194MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:57:16] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4182 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:02] [W] [TRT] Tactic Device request: 4764MB Available: 2303MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:02] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4764 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:02] [W] [TRT] Tactic Device request: 4764MB Available: 2303MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:02] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4764 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:02] [W] [TRT] Tactic Device request: 4764MB Available: 2303MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:02] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4764 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:04] [W] [TRT] Tactic Device request: 4761MB Available: 2316MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:04] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4761 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:04] [W] [TRT] Tactic Device request: 4761MB Available: 2317MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:04] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4761 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:10] [W] [TRT] Tactic Device request: 4244MB Available: 2261MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:10] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4244 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:11] [W] [TRT] Tactic Device request: 4244MB Available: 1947MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:11] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4244 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:12] [W] [TRT] Tactic Device request: 4244MB Available: 1942MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:12] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4244 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:17] [W] [TRT] Tactic Device request: 4240MB Available: 1944MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:17] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4240 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:17] [W] [TRT] Tactic Device request: 4240MB Available: 1931MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:17] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4240 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:20] [W] [TRT] Tactic Device request: 4241MB Available: 1926MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:21] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4241 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:21] [W] [TRT] Tactic Device request: 4241MB Available: 1894MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:21] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4241 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:22] [W] [TRT] Tactic Device request: 4241MB Available: 1891MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:22] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4241 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:27] [W] [TRT] Tactic Device request: 4239MB Available: 1889MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:27] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4239 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:05:27] [W] [TRT] Tactic Device request: 4239MB Available: 1877MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:05:27] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4239 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:06:08] [W] [TRT] Tactic Device request: 1637MB Available: 1622MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:06:08] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 1637 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:06:08] [W] [TRT] Tactic Device request: 1637MB Available: 1622MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:06:08] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 1637 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:06:08] [W] [TRT] Tactic Device request: 1637MB Available: 1622MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:06:08] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 1637 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:06:09] [W] [TRT] Tactic Device request: 1636MB Available: 1622MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:06:09] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 1636 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:06:09] [W] [TRT] Tactic Device request: 1636MB Available: 1622MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:06:09] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 1636 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:44] [W] [TRT] Tactic Device request: 1638MB Available: 1488MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:44] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 1638 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:44] [W] [TRT] Tactic Device request: 1638MB Available: 1488MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:44] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 1638 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:44] [W] [TRT] Tactic Device request: 1637MB Available: 1489MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:44] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 1637 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:45] [W] [TRT] Tactic Device request: 1637MB Available: 1489MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:45] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 1637 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:46] [W] [TRT] Tactic Device request: 3270MB Available: 1488MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:46] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3270 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:46] [W] [TRT] Tactic Device request: 3270MB Available: 1488MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:46] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3270 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:46] [W] [TRT] Tactic Device request: 3270MB Available: 1488MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:46] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3270 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:47] [W] [TRT] Tactic Device request: 3269MB Available: 1519MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:47] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3269 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:47] [W] [TRT] Tactic Device request: 3269MB Available: 1518MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:47] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3269 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:50] [W] [TRT] Tactic Device request: 4377MB Available: 1700MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:50] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4377 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:50] [W] [TRT] Tactic Device request: 2185MB Available: 1700MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:50] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2185 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:50] [W] [TRT] Tactic Device request: 4377MB Available: 1700MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:50] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4377 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:50] [W] [TRT] Tactic Device request: 2185MB Available: 1699MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:50] [W] [TRT] Skipping tactic 10 due to insufficient memory on requested size of 2185 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:51] [W] [TRT] Tactic Device request: 4377MB Available: 1699MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:51] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4377 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:51] [W] [TRT] Tactic Device request: 2185MB Available: 1699MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:51] [W] [TRT] Skipping tactic 16 due to insufficient memory on requested size of 2185 detected for tactic 0x0000000000000075.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:56] [W] [TRT] Tactic Device request: 4375MB Available: 1824MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:56] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4375 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:56] [W] [TRT] Tactic Device request: 2183MB Available: 1824MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:57] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2183 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:57] [W] [TRT] Tactic Device request: 4375MB Available: 1824MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:57] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4375 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:13:57] [W] [TRT] Tactic Device request: 2183MB Available: 1824MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:13:57] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2183 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:14:01] [W] [TRT] Tactic Device request: 4376MB Available: 1823MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:14:01] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4376 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:14:01] [W] [TRT] Tactic Device request: 2184MB Available: 1823MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:14:01] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2184 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:14:01] [W] [TRT] Tactic Device request: 4376MB Available: 1823MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:14:01] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4376 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:14:01] [W] [TRT] Tactic Device request: 2184MB Available: 1823MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:14:01] [W] [TRT] Skipping tactic 10 due to insufficient memory on requested size of 2184 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:14:01] [W] [TRT] Tactic Device request: 4376MB Available: 1822MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:14:01] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4376 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:14:01] [W] [TRT] Tactic Device request: 2184MB Available: 1823MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:14:01] [W] [TRT] Skipping tactic 16 due to insufficient memory on requested size of 2184 detected for tactic 0x0000000000000075.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:14:07] [W] [TRT] Tactic Device request: 4375MB Available: 1822MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:14:07] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4375 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:14:07] [W] [TRT] Tactic Device request: 2183MB Available: 1822MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:14:07] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2183 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:14:07] [W] [TRT] Tactic Device request: 4375MB Available: 1822MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:14:07] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4375 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:14:07] [W] [TRT] Tactic Device request: 2183MB Available: 1821MB. Device memory is insufficient to use tactic.
+[12/28/2023-17:14:07] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2183 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-17:15:12] [W] * Throughput may be bound by Enqueue Time rather than GPU Compute and the GPU may be under-utilized.
+[12/28/2023-17:15:12] [W]   If not already in use, --useCudaGraph (utilize CUDA graphs where possible) may increase the throughput.
+[12/28/2023-17:15:12] [W] * GPU compute time is unstable, with coefficient of variance = 5.39183%.
+[12/28/2023-17:15:12] [W]   If not already in use, locking GPU clock frequency or adding --useSpinWait may improve the stability.

yolo_nas_pose_l_fp16.onnx.fp16.engine.log

@@ -0,0 +1,328 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp16.onnx --fp16 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp16.onnx.fp16.engine
+[12/28/2023-16:09:46] [I] === Model Options ===
+[12/28/2023-16:09:46] [I] Format: ONNX
+[12/28/2023-16:09:46] [I] Model: yolo_nas_pose_l_fp16.onnx
+[12/28/2023-16:09:46] [I] Output:
+[12/28/2023-16:09:46] [I] === Build Options ===
+[12/28/2023-16:09:46] [I] Max batch: explicit batch
+[12/28/2023-16:09:46] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-16:09:46] [I] minTiming: 1
+[12/28/2023-16:09:46] [I] avgTiming: 8
+[12/28/2023-16:09:46] [I] Precision: FP32+FP16
+[12/28/2023-16:09:46] [I] LayerPrecisions: 
+[12/28/2023-16:09:46] [I] Calibration: 
+[12/28/2023-16:09:46] [I] Refit: Disabled
+[12/28/2023-16:09:46] [I] Sparsity: Disabled
+[12/28/2023-16:09:46] [I] Safe mode: Disabled
+[12/28/2023-16:09:46] [I] DirectIO mode: Disabled
+[12/28/2023-16:09:46] [I] Restricted mode: Disabled
+[12/28/2023-16:09:46] [I] Build only: Disabled
+[12/28/2023-16:09:46] [I] Save engine: yolo_nas_pose_l_fp16.onnx.fp16.engine
+[12/28/2023-16:09:46] [I] Load engine: 
+[12/28/2023-16:09:46] [I] Profiling verbosity: 0
+[12/28/2023-16:09:46] [I] Tactic sources: Using default tactic sources
+[12/28/2023-16:09:46] [I] timingCacheMode: local
+[12/28/2023-16:09:46] [I] timingCacheFile: 
+[12/28/2023-16:09:46] [I] Heuristic: Disabled
+[12/28/2023-16:09:46] [I] Preview Features: Use default preview flags.
+[12/28/2023-16:09:46] [I] Input(s)s format: fp32:CHW
+[12/28/2023-16:09:46] [I] Output(s)s format: fp32:CHW
+[12/28/2023-16:09:46] [I] Input build shapes: model
+[12/28/2023-16:09:46] [I] Input calibration shapes: model
+[12/28/2023-16:09:46] [I] === System Options ===
+[12/28/2023-16:09:46] [I] Device: 0
+[12/28/2023-16:09:46] [I] DLACore: 
+[12/28/2023-16:09:46] [I] Plugins:
+[12/28/2023-16:09:46] [I] === Inference Options ===
+[12/28/2023-16:09:46] [I] Batch: Explicit
+[12/28/2023-16:09:46] [I] Input inference shapes: model
+[12/28/2023-16:09:46] [I] Iterations: 10
+[12/28/2023-16:09:46] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-16:09:46] [I] Sleep time: 0ms
+[12/28/2023-16:09:46] [I] Idle time: 0ms
+[12/28/2023-16:09:46] [I] Streams: 1
+[12/28/2023-16:09:46] [I] ExposeDMA: Disabled
+[12/28/2023-16:09:46] [I] Data transfers: Enabled
+[12/28/2023-16:09:46] [I] Spin-wait: Disabled
+[12/28/2023-16:09:46] [I] Multithreading: Disabled
+[12/28/2023-16:09:46] [I] CUDA Graph: Disabled
+[12/28/2023-16:09:46] [I] Separate profiling: Disabled
+[12/28/2023-16:09:46] [I] Time Deserialize: Disabled
+[12/28/2023-16:09:46] [I] Time Refit: Disabled
+[12/28/2023-16:09:46] [I] NVTX verbosity: 0
+[12/28/2023-16:09:46] [I] Persistent Cache Ratio: 0
+[12/28/2023-16:09:46] [I] Inputs:
+[12/28/2023-16:09:46] [I] === Reporting Options ===
+[12/28/2023-16:09:46] [I] Verbose: Disabled
+[12/28/2023-16:09:46] [I] Averages: 100 inferences
+[12/28/2023-16:09:46] [I] Percentiles: 90,95,99
+[12/28/2023-16:09:46] [I] Dump refittable layers:Disabled
+[12/28/2023-16:09:46] [I] Dump output: Disabled
+[12/28/2023-16:09:46] [I] Profile: Disabled
+[12/28/2023-16:09:46] [I] Export timing to JSON file: 
+[12/28/2023-16:09:46] [I] Export output to JSON file: 
+[12/28/2023-16:09:46] [I] Export profile to JSON file: 
+[12/28/2023-16:09:46] [I] 
+[12/28/2023-16:09:46] [I] === Device Information ===
+[12/28/2023-16:09:46] [I] Selected Device: Orin
+[12/28/2023-16:09:46] [I] Compute Capability: 8.7
+[12/28/2023-16:09:46] [I] SMs: 8
+[12/28/2023-16:09:46] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-16:09:46] [I] Device Global Memory: 7471 MiB
+[12/28/2023-16:09:46] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-16:09:46] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-16:09:46] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-16:09:46] [I] 
+[12/28/2023-16:09:46] [I] TensorRT version: 8.5.2
+[12/28/2023-16:09:46] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 2974 (MiB)
+[12/28/2023-16:09:49] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +283, now: CPU 574, GPU 3280 (MiB)
+[12/28/2023-16:09:49] [I] Start parsing network model
+[12/28/2023-16:09:49] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-16:09:49] [I] [TRT] Input filename:   yolo_nas_pose_l_fp16.onnx
+[12/28/2023-16:09:49] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-16:09:49] [I] [TRT] Opset version:    17
+[12/28/2023-16:09:49] [I] [TRT] Producer name:    pytorch
+[12/28/2023-16:09:49] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-16:09:49] [I] [TRT] Domain:           
+[12/28/2023-16:09:49] [I] [TRT] Model version:    0
+[12/28/2023-16:09:49] [I] [TRT] Doc string:       
+[12/28/2023-16:09:49] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-16:09:49] [I] Finish parsing network model
+[12/28/2023-16:09:50] [I] [TRT] ---------- Layers Running on DLA ----------
+[12/28/2023-16:09:50] [I] [TRT] ---------- Layers Running on GPU ----------
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation1]
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/pre_process/pre_process.0/Cast.../pre_process/pre_process.2/Mul]}
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 458) [Constant]
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 459) [Constant]
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 460) [Constant]
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stem/conv/rbr_reparam/Conv + /model/backbone/stem/conv/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/downsample/rbr_reparam/Conv + /model/backbone/stage1/downsample/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv2/conv/Conv + /model/backbone/stage1/blocks/conv2/act/Relu || /model/backbone/stage1/blocks/conv1/conv/Conv + /model/backbone/stage1/blocks/conv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 15) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 23) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv3/conv/Conv + /model/backbone/stage1/blocks/conv3/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_skip2/conv/Conv + /model/neck/neck2/reduce_skip2/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/downsample/rbr_reparam/Conv + /model/backbone/stage2/downsample/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/downsample/conv/Conv + /model/neck/neck2/downsample/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv2/conv/Conv + /model/backbone/stage2/blocks/conv2/act/Relu || /model/backbone/stage2/blocks/conv1/conv/Conv + /model/backbone/stage2/blocks/conv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 44) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 52) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 60) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv3/conv/Conv + /model/backbone/stage2/blocks/conv3/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip2/conv/Conv + /model/neck/neck1/reduce_skip2/act/Relu || /model/neck/neck2/reduce_skip1/conv/Conv + /model/neck/neck2/reduce_skip1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/downsample/rbr_reparam/Conv + /model/backbone/stage3/downsample/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/downsample/conv/Conv + /model/neck/neck1/downsample/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv2/conv/Conv + /model/backbone/stage3/blocks/conv2/act/Relu || /model/backbone/stage3/blocks/conv1/conv/Conv + /model/backbone/stage3/blocks/conv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 83) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 91) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 99) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 107) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.4.alpha + (Unnamed Layer* 115) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv3/conv/Conv + /model/backbone/stage3/blocks/conv3/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip1/conv/Conv + /model/neck/neck1/reduce_skip1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/downsample/rbr_reparam/Conv + /model/backbone/stage4/downsample/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv2/conv/Conv + /model/backbone/stage4/blocks/conv2/act/Relu || /model/backbone/stage4/blocks/conv1/conv/Conv + /model/backbone/stage4/blocks/conv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 134) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 142) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv3/conv/Conv + /model/backbone/stage4/blocks/conv3/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv1/conv/Conv + /model/backbone/context_module/cv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.2/MaxPool
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.1/MaxPool
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.0/MaxPool
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/backbone/context_module/cv1/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv2/conv/Conv + /model/backbone/context_module/cv2/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/conv/conv/Conv + /model/neck/neck1/conv/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck1/upsample/ConvTranspose
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_after_concat/conv/Conv + /model/neck/neck1/reduce_after_concat/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv2/conv/Conv + /model/neck/neck1/blocks/conv2/act/Relu || /model/neck/neck1/blocks/conv1/conv/Conv + /model/neck/neck1/blocks/conv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 171) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 179) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.2.alpha + (Unnamed Layer* 187) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.3.alpha + (Unnamed Layer* 195) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv3/conv/Conv + /model/neck/neck1/blocks/conv3/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/conv/conv/Conv + /model/neck/neck2/conv/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck2/upsample/ConvTranspose
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/reduce_skip1/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_after_concat/conv/Conv + /model/neck/neck2/reduce_after_concat/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv2/conv/Conv + /model/neck/neck2/blocks/conv2/act/Relu || /model/neck/neck2/blocks/conv1/conv/Conv + /model/neck/neck2/blocks/conv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 216) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 224) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 232) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.3.alpha + (Unnamed Layer* 240) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv3/conv/Conv + /model/neck/neck2/blocks/conv3/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/bbox_stem/seq/conv/Conv + /model/heads/head1/bbox_stem/seq/act/Relu || /model/heads/head1/pose_stem/seq/conv/Conv + /model/heads/head1/pose_stem/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/conv/conv/Conv + /model/neck/neck3/conv/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head1/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head1/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head1/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv2/conv/Conv + /model/neck/neck3/blocks/conv2/act/Relu || /model/neck/neck3/blocks/conv1/conv/Conv + /model/neck/neck3/blocks/conv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/cls_pred/Conv
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_pred/Conv
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape + /model/heads/Transpose
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_pred/Conv
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 271) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 294) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 302) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 310) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv3/conv/Conv + /model/neck/neck3/blocks/conv3/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_stem/seq/conv/Conv + /model/heads/head2/pose_stem/seq/act/Relu || /model/heads/head2/bbox_stem/seq/conv/Conv + /model/heads/head2/bbox_stem/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/conv/conv/Conv + /model/neck/neck4/conv/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head2/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head2/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head2/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv2/conv/Conv + /model/neck/neck4/blocks/conv2/act/Relu || /model/neck/neck4/blocks/conv1/conv/Conv + /model/neck/neck4/blocks/conv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/cls_pred/Conv
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_pred/Conv
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_4 + /model/heads/Transpose_3
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_pred/Conv
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_1
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 341) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_1
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 364) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.2.alpha + (Unnamed Layer* 372) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.3.alpha + (Unnamed Layer* 380) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv3/conv/Conv + /model/neck/neck4/blocks/conv3/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/bbox_stem/seq/conv/Conv + /model/heads/head3/bbox_stem/seq/act/Relu || /model/heads/head3/pose_stem/seq/conv/Conv + /model/heads/head3/pose_stem/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head3/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head3/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head3/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/cls_pred/Conv
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_pred/Conv
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_8 + /model/heads/Transpose_6
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.2/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.2/seq/act/Relu
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_2
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_pred/Conv
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_2
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice_1...cast_boxes_to_fp32]}
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] NMS: batched_nms_26
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] DEVICE_TO_SHAPE_HOST: (Unnamed Layer* 462) [NMS]_1_output[DevicetoShapeHostCopy]
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation2]
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice...graph2_/Concat_5]}
+[12/28/2023-16:09:50] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation3]
+[12/28/2023-16:10:01] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +534, GPU +353, now: CPU 1231, GPU 3827 (MiB)
+[12/28/2023-16:10:03] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +82, GPU +65, now: CPU 1313, GPU 3892 (MiB)
+[12/28/2023-16:10:03] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
+[12/28/2023-17:14:35] [I] [TRT] Total Activation Memory: 8058785792
+[12/28/2023-17:14:35] [I] [TRT] Detected 1 inputs and 1 output network tensors.
+[12/28/2023-17:14:49] [I] [TRT] Total Host Persistent Memory: 387328
+[12/28/2023-17:14:49] [I] [TRT] Total Device Persistent Memory: 51712
+[12/28/2023-17:14:49] [I] [TRT] Total Scratch Memory: 134217728
+[12/28/2023-17:14:49] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 69 MiB, GPU 2131 MiB
+[12/28/2023-17:14:49] [I] [TRT] [BlockAssignment] Started assigning block shifts. This will take 196 steps to complete.
+[12/28/2023-17:14:49] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 90.8216ms to assign 13 blocks to 196 nodes requiring 160489472 bytes.
+[12/28/2023-17:14:49] [I] [TRT] Total Activation Memory: 160489472
+[12/28/2023-17:14:55] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU -16, now: CPU 1661, GPU 5679 (MiB)
+[12/28/2023-17:14:55] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +16, GPU +128, now: CPU 16, GPU 128 (MiB)
+[12/28/2023-17:14:55] [I] Engine built in 3909.9 sec.
+[12/28/2023-17:14:56] [I] [TRT] Loaded engine size: 105 MiB
+[12/28/2023-17:14:56] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1347, GPU 5281 (MiB)
+[12/28/2023-17:14:56] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +103, now: CPU 0, GPU 103 (MiB)
+[12/28/2023-17:14:56] [I] Engine deserialized in 0.281193 sec.
+[12/28/2023-17:14:56] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU -1, now: CPU 1348, GPU 5280 (MiB)
+[12/28/2023-17:14:56] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +154, now: CPU 0, GPU 257 (MiB)
+[12/28/2023-17:14:56] [I] Setting persistentCacheLimit to 0 bytes.
+[12/28/2023-17:14:56] [I] Using random values for input onnx::Cast_0
+[12/28/2023-17:14:56] [I] Created input binding for onnx::Cast_0 with dimensions 1x3x640x640
+[12/28/2023-17:14:56] [I] Using random values for output graph2_flat_predictions
+[12/28/2023-17:14:56] [I] Created output binding for graph2_flat_predictions with dimensions -1x57
+[12/28/2023-17:14:56] [I] Starting inference
+[12/28/2023-17:15:12] [I] Warmup completed 1 queries over 200 ms
+[12/28/2023-17:15:12] [I] Timing trace has 446 queries over 15.0628 s
+[12/28/2023-17:15:12] [I] 
+[12/28/2023-17:15:12] [I] === Trace details ===
+[12/28/2023-17:15:12] [I] Trace averages of 100 runs:
+[12/28/2023-17:15:12] [I] Average on 100 runs - GPU latency: 33.8846 ms - Host latency: 34.0014 ms (enqueue 33.9409 ms)
+[12/28/2023-17:15:12] [I] Average on 100 runs - GPU latency: 33.6823 ms - Host latency: 33.7942 ms (enqueue 33.7436 ms)
+[12/28/2023-17:15:12] [I] Average on 100 runs - GPU latency: 33.5307 ms - Host latency: 33.6433 ms (enqueue 33.5802 ms)
+[12/28/2023-17:15:12] [I] Average on 100 runs - GPU latency: 33.377 ms - Host latency: 33.4884 ms (enqueue 33.4514 ms)
+[12/28/2023-17:15:12] [I] 
+[12/28/2023-17:15:12] [I] === Performance summary ===
+[12/28/2023-17:15:12] [I] Throughput: 29.6093 qps
+[12/28/2023-17:15:12] [I] Latency: min = 31.7529 ms, max = 44.1514 ms, mean = 33.7469 ms, median = 33.4268 ms, percentile(90%) = 34.5583 ms, percentile(95%) = 37.8339 ms, percentile(99%) = 42.0027 ms
+[12/28/2023-17:15:12] [I] Enqueue Time: min = 31.7227 ms, max = 44.1133 ms, mean = 33.6924 ms, median = 33.4424 ms, percentile(90%) = 34.3545 ms, percentile(95%) = 37.7542 ms, percentile(99%) = 41.9526 ms
+[12/28/2023-17:15:12] [I] H2D Latency: min = 0.0800781 ms, max = 0.114746 ms, mean = 0.0954138 ms, median = 0.0969238 ms, percentile(90%) = 0.100098 ms, percentile(95%) = 0.100586 ms, percentile(99%) = 0.103027 ms
+[12/28/2023-17:15:12] [I] GPU Compute Time: min = 31.6406 ms, max = 44.0381 ms, mean = 33.6343 ms, median = 33.311 ms, percentile(90%) = 34.4478 ms, percentile(95%) = 37.7091 ms, percentile(99%) = 41.8918 ms
+[12/28/2023-17:15:12] [I] D2H Latency: min = 0.00292969 ms, max = 0.0541992 ms, mean = 0.017179 ms, median = 0.0146484 ms, percentile(90%) = 0.0290527 ms, percentile(95%) = 0.0314941 ms, percentile(99%) = 0.0361328 ms
+[12/28/2023-17:15:12] [I] Total Host Walltime: 15.0628 s
+[12/28/2023-17:15:12] [I] Total GPU Compute Time: 15.0009 s
+[12/28/2023-17:15:12] [I] Explanations of the performance metrics are printed in the verbose logs.
+[12/28/2023-17:15:12] [I] 
+&&&& PASSED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp16.onnx --fp16 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp16.onnx.fp16.engine

yolo_nas_pose_l_fp16.onnx.int8.engine.err

@@ -0,0 +1,8 @@
+[12/28/2023-19:27:13] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-19:27:13] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-19:27:13] [E] Error[4]: [network.cpp::validate::2925] Error Code 4: Internal Error (fp16 precision has been set for a layer or layer output, but fp16 is not configured in the builder)
+[12/28/2023-19:27:13] [E] Error[2]: [builder.cpp::buildSerializedNetwork::751] Error Code 2: Internal Error (Assertion engine != nullptr failed. )
+[12/28/2023-19:27:13] [E] Engine could not be created from network
+[12/28/2023-19:27:13] [E] Building engine failed
+[12/28/2023-19:27:13] [E] Failed to create engine from model or file.
+[12/28/2023-19:27:13] [E] Engine set up failed

yolo_nas_pose_l_fp16.onnx.int8.engine.log

@@ -0,0 +1,92 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp16.onnx --int8 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp16.onnx.int8.engine
+[12/28/2023-19:27:02] [I] === Model Options ===
+[12/28/2023-19:27:02] [I] Format: ONNX
+[12/28/2023-19:27:02] [I] Model: yolo_nas_pose_l_fp16.onnx
+[12/28/2023-19:27:02] [I] Output:
+[12/28/2023-19:27:02] [I] === Build Options ===
+[12/28/2023-19:27:02] [I] Max batch: explicit batch
+[12/28/2023-19:27:02] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-19:27:02] [I] minTiming: 1
+[12/28/2023-19:27:02] [I] avgTiming: 8
+[12/28/2023-19:27:02] [I] Precision: FP32+INT8
+[12/28/2023-19:27:02] [I] LayerPrecisions: 
+[12/28/2023-19:27:02] [I] Calibration: Dynamic
+[12/28/2023-19:27:02] [I] Refit: Disabled
+[12/28/2023-19:27:02] [I] Sparsity: Disabled
+[12/28/2023-19:27:02] [I] Safe mode: Disabled
+[12/28/2023-19:27:02] [I] DirectIO mode: Disabled
+[12/28/2023-19:27:02] [I] Restricted mode: Disabled
+[12/28/2023-19:27:02] [I] Build only: Disabled
+[12/28/2023-19:27:02] [I] Save engine: yolo_nas_pose_l_fp16.onnx.int8.engine
+[12/28/2023-19:27:02] [I] Load engine: 
+[12/28/2023-19:27:02] [I] Profiling verbosity: 0
+[12/28/2023-19:27:02] [I] Tactic sources: Using default tactic sources
+[12/28/2023-19:27:02] [I] timingCacheMode: local
+[12/28/2023-19:27:02] [I] timingCacheFile: 
+[12/28/2023-19:27:02] [I] Heuristic: Disabled
+[12/28/2023-19:27:02] [I] Preview Features: Use default preview flags.
+[12/28/2023-19:27:02] [I] Input(s)s format: fp32:CHW
+[12/28/2023-19:27:02] [I] Output(s)s format: fp32:CHW
+[12/28/2023-19:27:02] [I] Input build shapes: model
+[12/28/2023-19:27:02] [I] Input calibration shapes: model
+[12/28/2023-19:27:02] [I] === System Options ===
+[12/28/2023-19:27:02] [I] Device: 0
+[12/28/2023-19:27:02] [I] DLACore: 
+[12/28/2023-19:27:02] [I] Plugins:
+[12/28/2023-19:27:02] [I] === Inference Options ===
+[12/28/2023-19:27:02] [I] Batch: Explicit
+[12/28/2023-19:27:02] [I] Input inference shapes: model
+[12/28/2023-19:27:02] [I] Iterations: 10
+[12/28/2023-19:27:02] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-19:27:02] [I] Sleep time: 0ms
+[12/28/2023-19:27:02] [I] Idle time: 0ms
+[12/28/2023-19:27:02] [I] Streams: 1
+[12/28/2023-19:27:02] [I] ExposeDMA: Disabled
+[12/28/2023-19:27:02] [I] Data transfers: Enabled
+[12/28/2023-19:27:02] [I] Spin-wait: Disabled
+[12/28/2023-19:27:02] [I] Multithreading: Disabled
+[12/28/2023-19:27:02] [I] CUDA Graph: Disabled
+[12/28/2023-19:27:02] [I] Separate profiling: Disabled
+[12/28/2023-19:27:02] [I] Time Deserialize: Disabled
+[12/28/2023-19:27:02] [I] Time Refit: Disabled
+[12/28/2023-19:27:02] [I] NVTX verbosity: 0
+[12/28/2023-19:27:02] [I] Persistent Cache Ratio: 0
+[12/28/2023-19:27:02] [I] Inputs:
+[12/28/2023-19:27:02] [I] === Reporting Options ===
+[12/28/2023-19:27:02] [I] Verbose: Disabled
+[12/28/2023-19:27:02] [I] Averages: 100 inferences
+[12/28/2023-19:27:02] [I] Percentiles: 90,95,99
+[12/28/2023-19:27:02] [I] Dump refittable layers:Disabled
+[12/28/2023-19:27:02] [I] Dump output: Disabled
+[12/28/2023-19:27:02] [I] Profile: Disabled
+[12/28/2023-19:27:02] [I] Export timing to JSON file: 
+[12/28/2023-19:27:02] [I] Export output to JSON file: 
+[12/28/2023-19:27:02] [I] Export profile to JSON file: 
+[12/28/2023-19:27:02] [I] 
+[12/28/2023-19:27:02] [I] === Device Information ===
+[12/28/2023-19:27:02] [I] Selected Device: Orin
+[12/28/2023-19:27:02] [I] Compute Capability: 8.7
+[12/28/2023-19:27:02] [I] SMs: 8
+[12/28/2023-19:27:02] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-19:27:02] [I] Device Global Memory: 7471 MiB
+[12/28/2023-19:27:02] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-19:27:02] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-19:27:02] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-19:27:02] [I] 
+[12/28/2023-19:27:02] [I] TensorRT version: 8.5.2
+[12/28/2023-19:27:07] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 2837 (MiB)
+[12/28/2023-19:27:11] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +285, now: CPU 574, GPU 3142 (MiB)
+[12/28/2023-19:27:11] [I] Start parsing network model
+[12/28/2023-19:27:12] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-19:27:12] [I] [TRT] Input filename:   yolo_nas_pose_l_fp16.onnx
+[12/28/2023-19:27:12] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-19:27:12] [I] [TRT] Opset version:    17
+[12/28/2023-19:27:12] [I] [TRT] Producer name:    pytorch
+[12/28/2023-19:27:12] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-19:27:12] [I] [TRT] Domain:           
+[12/28/2023-19:27:12] [I] [TRT] Model version:    0
+[12/28/2023-19:27:12] [I] [TRT] Doc string:       
+[12/28/2023-19:27:12] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-19:27:13] [I] Finish parsing network model
+[12/28/2023-19:27:13] [I] FP32 and INT8 precisions have been specified - more performance might be enabled by additionally specifying --fp16 or --best
+&&&& FAILED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp16.onnx --int8 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp16.onnx.int8.engine

yolo_nas_pose_l_fp16.onnx.usage.txt

@@ -0,0 +1,58 @@
+
+Model exported successfully to yolo_nas_pose_l_fp16.onnx
+Model expects input image of shape [1, 3, 640, 640]
+Input image dtype is torch.uint8
+
+Exported model already contains preprocessing (normalization) step, so you don't need to do it manually.
+Preprocessing steps to be applied to input image are:
+Sequential(
+  (0): CastTensorTo(dtype=torch.float16)
+  (1): ChannelSelect(channels_indexes=tensor([2, 1, 0], device='cuda:0'))
+  (2): ApplyMeanStd(mean=[0.], scale=[255.])
+)
+
+
+Exported model contains postprocessing (NMS) step with the following parameters:
+    num_pre_nms_predictions=1000
+    max_predictions_per_image=10
+    nms_threshold=0.5
+    confidence_threshold=0.15
+    output_predictions_format=flat
+
+
+Exported model is in ONNX format and can be used with ONNXRuntime
+To run inference with ONNXRuntime, please use the following code snippet:
+
+    import onnxruntime
+    import numpy as np
+    session = onnxruntime.InferenceSession("yolo_nas_pose_l_fp16.onnx", providers=["CUDAExecutionProvider", "CPUExecutionProvider"])
+    inputs = [o.name for o in session.get_inputs()]
+    outputs = [o.name for o in session.get_outputs()]
+
+    example_input_image = np.zeros((1, 3, 640, 640)).astype(np.uint8)
+    predictions = session.run(outputs, {inputs[0]: example_input_image})
+
+Exported model can also be used with TensorRT
+To run inference with TensorRT, please see TensorRT deployment documentation
+You can benchmark the model using the following code snippet:
+
+    trtexec --onnx=yolo_nas_pose_l_fp16.onnx --fp16 --avgRuns=100 --duration=15
+
+
+Exported model has predictions in flat format:
+
+# flat_predictions is a 2D array of [N,K] shape
+# Each row represents (image_index, x_min, y_min, x_max, y_max, confidence, joints...)
+# Please note all values are floats, so you have to convert them to integers if needed
+
+[flat_predictions] = predictions
+pred_bboxes = flat_predictions[:, 1:5]
+pred_scores = flat_predictions[:, 5]
+pred_joints = flat_predictions[:, 6:].reshape((len(pred_bboxes), -1, 3))
+for i in range(len(pred_bboxes)):
+    confidence = pred_scores[i]
+    x_min, y_min, x_max, y_max = pred_bboxes[i]
+    print(f"Detected pose with confidence={{confidence}}, x_min={{x_min}}, y_min={{y_min}}, x_max={{x_max}}, y_max={{y_max}}")
+    for joint_index, (x, y, confidence) in enumerate(pred_joints[i]):")
+        print(f"Joint {{joint_index}} has coordinates x={{x}}, y={{y}}, confidence={{confidence}}")
+

yolo_nas_pose_l_fp32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd7c12de1275152ce64af33b734c74c085ed45403fb2722385718850a71f363
+size 217830699

yolo_nas_pose_l_fp32.onnx.best.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dea7e820c1d67f86f3b4c5749752351cb53d4f31886b72214b78d0621b27957f
+size 57142878

yolo_nas_pose_l_fp32.onnx.best.engine.err

@@ -0,0 +1,504 @@
+[12/28/2023-12:58:51] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-12:58:51] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-12:58:51] [W] [TRT] Calibrator is not being used. Users must provide dynamic range for all tensors that are not Int32 or Bool.
+[12/28/2023-13:32:07] [W] [TRT] Tactic Device request: 4720MB Available: 2945MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:07] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4720 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:07] [W] [TRT] Tactic Device request: 4720MB Available: 2943MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:07] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4720 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:08] [W] [TRT] Tactic Device request: 4720MB Available: 2943MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:08] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4720 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:13] [W] [TRT] Tactic Device request: 4706MB Available: 2945MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:13] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4706 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:14] [W] [TRT] Tactic Device request: 4706MB Available: 2944MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:14] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4706 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:18] [W] [TRT] Tactic Device request: 4711MB Available: 2921MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:18] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:19] [W] [TRT] Tactic Device request: 4711MB Available: 2920MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:19] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:19] [W] [TRT] Tactic Device request: 4711MB Available: 2919MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:19] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:24] [W] [TRT] Tactic Device request: 4702MB Available: 2920MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:24] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4702 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:25] [W] [TRT] Tactic Device request: 4702MB Available: 2921MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:25] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4702 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:29] [W] [TRT] Tactic Device request: 4711MB Available: 2875MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:29] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:30] [W] [TRT] Tactic Device request: 4711MB Available: 2875MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:30] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:30] [W] [TRT] Tactic Device request: 4711MB Available: 2874MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:30] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:35] [W] [TRT] Tactic Device request: 4702MB Available: 2874MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:35] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4702 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:32:36] [W] [TRT] Tactic Device request: 4702MB Available: 2874MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:32:36] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4702 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:40:10] [W] [TRT] Tactic Device request: 4711MB Available: 2317MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:40:10] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:40:10] [W] [TRT] Tactic Device request: 4711MB Available: 2317MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:40:11] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:40:11] [W] [TRT] Tactic Device request: 4711MB Available: 2317MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:40:11] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:40:13] [W] [TRT] Tactic Device request: 4701MB Available: 2317MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:40:13] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4701 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:40:13] [W] [TRT] Tactic Device request: 4701MB Available: 2316MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:40:13] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4701 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:40:32] [W] [TRT] Tactic Device request: 6275MB Available: 2317MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:40:32] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:40:32] [W] [TRT] Tactic Device request: 6275MB Available: 2317MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:40:32] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6275 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:40:32] [W] [TRT] Tactic Device request: 6275MB Available: 2317MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:40:32] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:40:34] [W] [TRT] Tactic Device request: 6270MB Available: 2318MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:40:34] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6270 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:40:34] [W] [TRT] Tactic Device request: 6270MB Available: 2318MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:40:34] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6270 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:21] [W] [TRT] Tactic Device request: 7056MB Available: 2081MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:21] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:21] [W] [TRT] Tactic Device request: 7056MB Available: 2081MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:21] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 7056 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:21] [W] [TRT] Tactic Device request: 7056MB Available: 2081MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:21] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:23] [W] [TRT] Tactic Device request: 7050MB Available: 2080MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:23] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7050 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:23] [W] [TRT] Tactic Device request: 7050MB Available: 2079MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:23] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 7050 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:44] [W] [TRT] Tactic Device request: 6354MB Available: 2081MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:44] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:45] [W] [TRT] Tactic Device request: 6354MB Available: 2081MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:45] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6354 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:45] [W] [TRT] Tactic Device request: 6354MB Available: 2081MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:45] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:47] [W] [TRT] Tactic Device request: 6351MB Available: 2080MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:47] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6351 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:47] [W] [TRT] Tactic Device request: 6351MB Available: 2080MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:47] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6351 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:49] [W] [TRT] Tactic Device request: 2127MB Available: 2079MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:49] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2127 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:50] [W] [TRT] Tactic Device request: 2127MB Available: 2078MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:50] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2127 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:50] [W] [TRT] Tactic Device request: 2127MB Available: 2078MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:50] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2127 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:53] [W] [TRT] Tactic Device request: 2124MB Available: 2081MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:53] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2124 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:53] [W] [TRT] Tactic Device request: 2124MB Available: 2072MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:53] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2124 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:56] [W] [TRT] Tactic Device request: 2125MB Available: 2070MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:56] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2125 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:56] [W] [TRT] Tactic Device request: 2125MB Available: 2052MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:56] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2125 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:57] [W] [TRT] Tactic Device request: 2125MB Available: 2052MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:57] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2125 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:51:59] [W] [TRT] Tactic Device request: 2124MB Available: 2053MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:51:59] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2124 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:52:00] [W] [TRT] Tactic Device request: 2124MB Available: 2051MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:52:00] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2124 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:52:02] [W] [TRT] Tactic Device request: 2125MB Available: 2051MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:52:02] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2125 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:52:03] [W] [TRT] Tactic Device request: 2125MB Available: 2051MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:52:03] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2125 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:52:03] [W] [TRT] Tactic Device request: 2125MB Available: 2051MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:52:03] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2125 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:52:06] [W] [TRT] Tactic Device request: 2124MB Available: 2039MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:52:06] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2124 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-13:52:06] [W] [TRT] Tactic Device request: 2124MB Available: 2038MB. Device memory is insufficient to use tactic.
+[12/28/2023-13:52:06] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2124 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:20] [W] [TRT] Tactic Device request: 2394MB Available: 1765MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:20] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2394 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:20] [W] [TRT] Tactic Device request: 2394MB Available: 1764MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:20] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2394 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:20] [W] [TRT] Tactic Device request: 2394MB Available: 1764MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:20] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2394 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:21] [W] [TRT] Tactic Device request: 2392MB Available: 1765MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:21] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:21] [W] [TRT] Tactic Device request: 2392MB Available: 1764MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:21] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2392 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:21] [W] [TRT] Tactic Device request: 2392MB Available: 1764MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:21] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:22] [W] [TRT] Tactic Device request: 2391MB Available: 1764MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:22] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2391 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:23] [W] [TRT] Tactic Device request: 2391MB Available: 1763MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:23] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2391 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:23] [W] [TRT] Tactic Device request: 2390MB Available: 1763MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:23] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2390 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:23] [W] [TRT] Tactic Device request: 2390MB Available: 1763MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:23] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2390 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:41] [W] [TRT] Tactic Device request: 6540MB Available: 1782MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:41] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6540 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:41] [W] [TRT] Tactic Device request: 6540MB Available: 1781MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:41] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6540 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:42] [W] [TRT] Tactic Device request: 6540MB Available: 1781MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:42] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6540 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:44] [W] [TRT] Tactic Device request: 6538MB Available: 1781MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:44] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6538 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:44] [W] [TRT] Tactic Device request: 6538MB Available: 1781MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:44] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6538 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:47] [W] [TRT] Tactic Device request: 2191MB Available: 1783MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:47] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2191 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:48] [W] [TRT] Tactic Device request: 2191MB Available: 1783MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:48] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2191 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:48] [W] [TRT] Tactic Device request: 2191MB Available: 1782MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:49] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2191 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:52] [W] [TRT] Tactic Device request: 2190MB Available: 1779MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:52] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:53] [W] [TRT] Tactic Device request: 2190MB Available: 1779MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:53] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:57] [W] [TRT] Tactic Device request: 2190MB Available: 1780MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:57] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:58] [W] [TRT] Tactic Device request: 2190MB Available: 1778MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:58] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:06:59] [W] [TRT] Tactic Device request: 2190MB Available: 1775MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:06:59] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:07:03] [W] [TRT] Tactic Device request: 2190MB Available: 1778MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:07:03] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:07:03] [W] [TRT] Tactic Device request: 2190MB Available: 1777MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:07:03] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:07:08] [W] [TRT] Tactic Device request: 2190MB Available: 1778MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:07:08] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:07:09] [W] [TRT] Tactic Device request: 2190MB Available: 1779MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:07:09] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:07:09] [W] [TRT] Tactic Device request: 2190MB Available: 1778MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:07:09] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:07:13] [W] [TRT] Tactic Device request: 2190MB Available: 1778MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:07:13] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:07:14] [W] [TRT] Tactic Device request: 2190MB Available: 1776MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:07:14] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:15:03] [W] [TRT] Tactic Device request: 2457MB Available: 2222MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:15:03] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:15:03] [W] [TRT] Tactic Device request: 2457MB Available: 2222MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:15:03] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2457 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:15:03] [W] [TRT] Tactic Device request: 2457MB Available: 2222MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:15:03] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:15:05] [W] [TRT] Tactic Device request: 2456MB Available: 2224MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:15:05] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2456 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:15:05] [W] [TRT] Tactic Device request: 2456MB Available: 2224MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:15:05] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2456 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:15:32] [W] [TRT] Tactic Device request: 3587MB Available: 1846MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:15:32] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:15:32] [W] [TRT] Tactic Device request: 3587MB Available: 1846MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:15:32] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3587 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:15:32] [W] [TRT] Tactic Device request: 3587MB Available: 1846MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:15:32] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:15:33] [W] [TRT] Tactic Device request: 3585MB Available: 1846MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:15:33] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3585 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:15:34] [W] [TRT] Tactic Device request: 3585MB Available: 1846MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:15:34] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3585 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:28:21] [W] [TRT] Tactic Device request: 3556MB Available: 1715MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:28:21] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:28:21] [W] [TRT] Tactic Device request: 3556MB Available: 1715MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:28:21] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3556 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:28:22] [W] [TRT] Tactic Device request: 3556MB Available: 1714MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:28:22] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:28:23] [W] [TRT] Tactic Device request: 3551MB Available: 1715MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:28:23] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3551 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:28:23] [W] [TRT] Tactic Device request: 3551MB Available: 1715MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:28:23] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3551 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:28:25] [W] [TRT] Tactic Device request: 3140MB Available: 1715MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:28:25] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3140 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:28:25] [W] [TRT] Tactic Device request: 3140MB Available: 1715MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:28:25] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3140 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:28:25] [W] [TRT] Tactic Device request: 3140MB Available: 1715MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:28:25] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3140 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:28:26] [W] [TRT] Tactic Device request: 3136MB Available: 1715MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:28:26] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3136 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:28:26] [W] [TRT] Tactic Device request: 3136MB Available: 1715MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:28:26] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3136 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:35] [W] [TRT] Tactic Device request: 3161MB Available: 2110MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:35] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3161 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:36] [W] [TRT] Tactic Device request: 3161MB Available: 2110MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:36] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3161 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:36] [W] [TRT] Tactic Device request: 3161MB Available: 2110MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:36] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3161 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:37] [W] [TRT] Tactic Device request: 3156MB Available: 2109MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:37] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3156 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:37] [W] [TRT] Tactic Device request: 3156MB Available: 2109MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:37] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3156 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:43] [W] [TRT] Tactic Device request: 4189MB Available: 2109MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:44] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4189 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:44] [W] [TRT] Tactic Device request: 4189MB Available: 2088MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:44] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4189 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:44] [W] [TRT] Tactic Device request: 4189MB Available: 2087MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:44] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4189 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:49] [W] [TRT] Tactic Device request: 4183MB Available: 2085MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:49] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4183 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:49] [W] [TRT] Tactic Device request: 4183MB Available: 2082MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:49] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4183 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:52] [W] [TRT] Tactic Device request: 4186MB Available: 2082MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:52] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4186 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:53] [W] [TRT] Tactic Device request: 4186MB Available: 2061MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:53] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4186 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:53] [W] [TRT] Tactic Device request: 4186MB Available: 2060MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:53] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4186 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:57] [W] [TRT] Tactic Device request: 4182MB Available: 2059MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:57] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4182 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:40:58] [W] [TRT] Tactic Device request: 4182MB Available: 2054MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:40:58] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4182 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:53:46] [W] [TRT] Tactic Device request: 4764MB Available: 2038MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:53:46] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4764 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:53:46] [W] [TRT] Tactic Device request: 4764MB Available: 2038MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:53:46] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4764 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:53:46] [W] [TRT] Tactic Device request: 4764MB Available: 2039MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:53:46] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4764 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:53:48] [W] [TRT] Tactic Device request: 4761MB Available: 2038MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:53:48] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4761 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:53:48] [W] [TRT] Tactic Device request: 4761MB Available: 2038MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:53:48] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4761 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:53:56] [W] [TRT] Tactic Device request: 4244MB Available: 1833MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:53:56] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4244 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:53:57] [W] [TRT] Tactic Device request: 4244MB Available: 1504MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:53:57] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4244 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:53:58] [W] [TRT] Tactic Device request: 4244MB Available: 1500MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:53:58] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4244 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:54:03] [W] [TRT] Tactic Device request: 4240MB Available: 1498MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:54:03] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4240 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:54:03] [W] [TRT] Tactic Device request: 4240MB Available: 1494MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:54:03] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4240 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:54:08] [W] [TRT] Tactic Device request: 4241MB Available: 1553MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:54:08] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4241 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:54:09] [W] [TRT] Tactic Device request: 4241MB Available: 1514MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:54:09] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4241 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:54:10] [W] [TRT] Tactic Device request: 4241MB Available: 1508MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:54:10] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4241 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:54:14] [W] [TRT] Tactic Device request: 4239MB Available: 1510MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:54:14] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4239 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:54:15] [W] [TRT] Tactic Device request: 4239MB Available: 1496MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:54:15] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4239 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:55:04] [W] [TRT] Tactic Device request: 1637MB Available: 1234MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:55:04] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 1637 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:55:04] [W] [TRT] Tactic Device request: 1637MB Available: 1234MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:55:04] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 1637 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:55:04] [W] [TRT] Tactic Device request: 1637MB Available: 1234MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:55:04] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 1637 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:55:05] [W] [TRT] Tactic Device request: 1636MB Available: 1268MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:55:05] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 1636 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-14:55:05] [W] [TRT] Tactic Device request: 1636MB Available: 1268MB. Device memory is insufficient to use tactic.
+[12/28/2023-14:55:05] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 1636 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:11] [W] [TRT] Tactic Device request: 1638MB Available: 1062MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:12] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 1638 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:12] [W] [TRT] Tactic Device request: 1638MB Available: 1063MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:12] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 1638 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:14] [W] [TRT] Tactic Device request: 1637MB Available: 1065MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:14] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 1637 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:14] [W] [TRT] Tactic Device request: 1637MB Available: 1065MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:14] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 1637 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:16] [W] [TRT] Tactic Device request: 3270MB Available: 1064MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:16] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3270 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:17] [W] [TRT] Tactic Device request: 3270MB Available: 1064MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:17] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3270 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:17] [W] [TRT] Tactic Device request: 3270MB Available: 1064MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:17] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3270 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:18] [W] [TRT] Tactic Device request: 3269MB Available: 1063MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:18] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3269 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:19] [W] [TRT] Tactic Device request: 3269MB Available: 1063MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:19] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3269 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:22] [W] [TRT] Tactic Device request: 4377MB Available: 1060MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:22] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4377 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:22] [W] [TRT] Tactic Device request: 2185MB Available: 1060MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:22] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2185 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:23] [W] [TRT] Tactic Device request: 4377MB Available: 1061MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:23] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4377 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:23] [W] [TRT] Tactic Device request: 2185MB Available: 1061MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:23] [W] [TRT] Skipping tactic 10 due to insufficient memory on requested size of 2185 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:23] [W] [TRT] Tactic Device request: 4377MB Available: 1060MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:23] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4377 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:23] [W] [TRT] Tactic Device request: 2185MB Available: 1060MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:23] [W] [TRT] Skipping tactic 16 due to insufficient memory on requested size of 2185 detected for tactic 0x0000000000000075.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:29] [W] [TRT] Tactic Device request: 4375MB Available: 1059MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:29] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4375 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:29] [W] [TRT] Tactic Device request: 2183MB Available: 1059MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:29] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2183 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:29] [W] [TRT] Tactic Device request: 4375MB Available: 1058MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:29] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4375 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:29] [W] [TRT] Tactic Device request: 2183MB Available: 1058MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:29] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2183 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:36] [W] [TRT] Tactic Device request: 4376MB Available: 1050MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:36] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4376 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:36] [W] [TRT] Tactic Device request: 2184MB Available: 1049MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:36] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2184 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:36] [W] [TRT] Tactic Device request: 4376MB Available: 1037MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:36] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4376 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:36] [W] [TRT] Tactic Device request: 2184MB Available: 1037MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:36] [W] [TRT] Skipping tactic 10 due to insufficient memory on requested size of 2184 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:37] [W] [TRT] Tactic Device request: 4376MB Available: 1036MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:37] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4376 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:37] [W] [TRT] Tactic Device request: 2184MB Available: 1036MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:37] [W] [TRT] Skipping tactic 16 due to insufficient memory on requested size of 2184 detected for tactic 0x0000000000000075.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:42] [W] [TRT] Tactic Device request: 4375MB Available: 1058MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:42] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4375 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:42] [W] [TRT] Tactic Device request: 2183MB Available: 1058MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:42] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2183 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:43] [W] [TRT] Tactic Device request: 4375MB Available: 1058MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:43] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4375 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:08:43] [W] [TRT] Tactic Device request: 2183MB Available: 1058MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:08:43] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2183 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:09:47] [W] [TRT] TensorRT encountered issues when converting weights between types and that could affect accuracy.
+[12/28/2023-15:09:47] [W] [TRT] If this is not the desired behavior, please modify the weights or retrain with regularization to adjust the magnitude of the weights.
+[12/28/2023-15:09:47] [W] [TRT] Check verbose logs for the list of affected weights.
+[12/28/2023-15:09:47] [W] [TRT] - 114 weights are affected by this issue: Detected subnormal FP16 values.
+[12/28/2023-15:09:47] [W] [TRT] - 40 weights are affected by this issue: Detected values less than smallest positive FP16 subnormal value and converted them to the FP16 minimum subnormalized value.
+[12/28/2023-15:10:04] [W] * Throughput may be bound by Enqueue Time rather than GPU Compute and the GPU may be under-utilized.
+[12/28/2023-15:10:04] [W]   If not already in use, --useCudaGraph (utilize CUDA graphs where possible) may increase the throughput.
+[12/28/2023-15:10:04] [W] * GPU compute time is unstable, with coefficient of variance = 7.00146%.
+[12/28/2023-15:10:04] [W]   If not already in use, locking GPU clock frequency or adding --useSpinWait may improve the stability.

yolo_nas_pose_l_fp32.onnx.best.engine.log

@@ -0,0 +1,331 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp32.onnx --best --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp32.onnx.best.engine
+[12/28/2023-12:58:38] [I] === Model Options ===
+[12/28/2023-12:58:38] [I] Format: ONNX
+[12/28/2023-12:58:38] [I] Model: yolo_nas_pose_l_fp32.onnx
+[12/28/2023-12:58:38] [I] Output:
+[12/28/2023-12:58:38] [I] === Build Options ===
+[12/28/2023-12:58:38] [I] Max batch: explicit batch
+[12/28/2023-12:58:38] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-12:58:38] [I] minTiming: 1
+[12/28/2023-12:58:38] [I] avgTiming: 8
+[12/28/2023-12:58:38] [I] Precision: FP32+FP16+INT8
+[12/28/2023-12:58:38] [I] LayerPrecisions: 
+[12/28/2023-12:58:38] [I] Calibration: Dynamic
+[12/28/2023-12:58:38] [I] Refit: Disabled
+[12/28/2023-12:58:38] [I] Sparsity: Disabled
+[12/28/2023-12:58:38] [I] Safe mode: Disabled
+[12/28/2023-12:58:38] [I] DirectIO mode: Disabled
+[12/28/2023-12:58:38] [I] Restricted mode: Disabled
+[12/28/2023-12:58:38] [I] Build only: Disabled
+[12/28/2023-12:58:38] [I] Save engine: yolo_nas_pose_l_fp32.onnx.best.engine
+[12/28/2023-12:58:38] [I] Load engine: 
+[12/28/2023-12:58:38] [I] Profiling verbosity: 0
+[12/28/2023-12:58:38] [I] Tactic sources: Using default tactic sources
+[12/28/2023-12:58:38] [I] timingCacheMode: local
+[12/28/2023-12:58:38] [I] timingCacheFile: 
+[12/28/2023-12:58:38] [I] Heuristic: Disabled
+[12/28/2023-12:58:38] [I] Preview Features: Use default preview flags.
+[12/28/2023-12:58:38] [I] Input(s)s format: fp32:CHW
+[12/28/2023-12:58:38] [I] Output(s)s format: fp32:CHW
+[12/28/2023-12:58:38] [I] Input build shapes: model
+[12/28/2023-12:58:38] [I] Input calibration shapes: model
+[12/28/2023-12:58:38] [I] === System Options ===
+[12/28/2023-12:58:38] [I] Device: 0
+[12/28/2023-12:58:38] [I] DLACore: 
+[12/28/2023-12:58:38] [I] Plugins:
+[12/28/2023-12:58:38] [I] === Inference Options ===
+[12/28/2023-12:58:38] [I] Batch: Explicit
+[12/28/2023-12:58:38] [I] Input inference shapes: model
+[12/28/2023-12:58:38] [I] Iterations: 10
+[12/28/2023-12:58:38] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-12:58:38] [I] Sleep time: 0ms
+[12/28/2023-12:58:38] [I] Idle time: 0ms
+[12/28/2023-12:58:38] [I] Streams: 1
+[12/28/2023-12:58:38] [I] ExposeDMA: Disabled
+[12/28/2023-12:58:38] [I] Data transfers: Enabled
+[12/28/2023-12:58:38] [I] Spin-wait: Disabled
+[12/28/2023-12:58:38] [I] Multithreading: Disabled
+[12/28/2023-12:58:38] [I] CUDA Graph: Disabled
+[12/28/2023-12:58:38] [I] Separate profiling: Disabled
+[12/28/2023-12:58:38] [I] Time Deserialize: Disabled
+[12/28/2023-12:58:38] [I] Time Refit: Disabled
+[12/28/2023-12:58:38] [I] NVTX verbosity: 0
+[12/28/2023-12:58:38] [I] Persistent Cache Ratio: 0
+[12/28/2023-12:58:38] [I] Inputs:
+[12/28/2023-12:58:38] [I] === Reporting Options ===
+[12/28/2023-12:58:38] [I] Verbose: Disabled
+[12/28/2023-12:58:38] [I] Averages: 100 inferences
+[12/28/2023-12:58:38] [I] Percentiles: 90,95,99
+[12/28/2023-12:58:38] [I] Dump refittable layers:Disabled
+[12/28/2023-12:58:38] [I] Dump output: Disabled
+[12/28/2023-12:58:38] [I] Profile: Disabled
+[12/28/2023-12:58:38] [I] Export timing to JSON file: 
+[12/28/2023-12:58:38] [I] Export output to JSON file: 
+[12/28/2023-12:58:38] [I] Export profile to JSON file: 
+[12/28/2023-12:58:38] [I] 
+[12/28/2023-12:58:38] [I] === Device Information ===
+[12/28/2023-12:58:38] [I] Selected Device: Orin
+[12/28/2023-12:58:38] [I] Compute Capability: 8.7
+[12/28/2023-12:58:38] [I] SMs: 8
+[12/28/2023-12:58:38] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-12:58:38] [I] Device Global Memory: 7471 MiB
+[12/28/2023-12:58:38] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-12:58:38] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-12:58:38] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-12:58:38] [I] 
+[12/28/2023-12:58:38] [I] TensorRT version: 8.5.2
+[12/28/2023-12:58:43] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 3010 (MiB)
+[12/28/2023-12:58:48] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +283, now: CPU 574, GPU 3313 (MiB)
+[12/28/2023-12:58:48] [I] Start parsing network model
+[12/28/2023-12:58:51] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-12:58:51] [I] [TRT] Input filename:   yolo_nas_pose_l_fp32.onnx
+[12/28/2023-12:58:51] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-12:58:51] [I] [TRT] Opset version:    17
+[12/28/2023-12:58:51] [I] [TRT] Producer name:    pytorch
+[12/28/2023-12:58:51] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-12:58:51] [I] [TRT] Domain:           
+[12/28/2023-12:58:51] [I] [TRT] Model version:    0
+[12/28/2023-12:58:51] [I] [TRT] Doc string:       
+[12/28/2023-12:58:51] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-12:58:51] [I] Finish parsing network model
+[12/28/2023-12:58:52] [I] [TRT] ---------- Layers Running on DLA ----------
+[12/28/2023-12:58:52] [I] [TRT] ---------- Layers Running on GPU ----------
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation1]
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/pre_process/pre_process.0/Cast.../pre_process/pre_process.2/Mul]}
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 455) [Constant]
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 456) [Constant]
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 457) [Constant]
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stem/conv/rbr_reparam/Conv + /model/backbone/stem/conv/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/downsample/rbr_reparam/Conv + /model/backbone/stage1/downsample/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv2/conv/Conv + /model/backbone/stage1/blocks/conv2/act/Relu || /model/backbone/stage1/blocks/conv1/conv/Conv + /model/backbone/stage1/blocks/conv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 15) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 23) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv3/conv/Conv + /model/backbone/stage1/blocks/conv3/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_skip2/conv/Conv + /model/neck/neck2/reduce_skip2/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/downsample/rbr_reparam/Conv + /model/backbone/stage2/downsample/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/downsample/conv/Conv + /model/neck/neck2/downsample/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv2/conv/Conv + /model/backbone/stage2/blocks/conv2/act/Relu || /model/backbone/stage2/blocks/conv1/conv/Conv + /model/backbone/stage2/blocks/conv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 44) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 52) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 60) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv3/conv/Conv + /model/backbone/stage2/blocks/conv3/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip2/conv/Conv + /model/neck/neck1/reduce_skip2/act/Relu || /model/neck/neck2/reduce_skip1/conv/Conv + /model/neck/neck2/reduce_skip1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/downsample/rbr_reparam/Conv + /model/backbone/stage3/downsample/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/downsample/conv/Conv + /model/neck/neck1/downsample/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv2/conv/Conv + /model/backbone/stage3/blocks/conv2/act/Relu || /model/backbone/stage3/blocks/conv1/conv/Conv + /model/backbone/stage3/blocks/conv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 83) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 91) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 99) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 107) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.4.alpha + (Unnamed Layer* 115) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv3/conv/Conv + /model/backbone/stage3/blocks/conv3/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip1/conv/Conv + /model/neck/neck1/reduce_skip1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/downsample/rbr_reparam/Conv + /model/backbone/stage4/downsample/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv2/conv/Conv + /model/backbone/stage4/blocks/conv2/act/Relu || /model/backbone/stage4/blocks/conv1/conv/Conv + /model/backbone/stage4/blocks/conv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 134) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 142) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv3/conv/Conv + /model/backbone/stage4/blocks/conv3/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv1/conv/Conv + /model/backbone/context_module/cv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.2/MaxPool
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.1/MaxPool
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.0/MaxPool
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/backbone/context_module/cv1/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv2/conv/Conv + /model/backbone/context_module/cv2/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/conv/conv/Conv + /model/neck/neck1/conv/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck1/upsample/ConvTranspose
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_after_concat/conv/Conv + /model/neck/neck1/reduce_after_concat/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv2/conv/Conv + /model/neck/neck1/blocks/conv2/act/Relu || /model/neck/neck1/blocks/conv1/conv/Conv + /model/neck/neck1/blocks/conv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 171) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 179) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.2.alpha + (Unnamed Layer* 187) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.3.alpha + (Unnamed Layer* 195) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv3/conv/Conv + /model/neck/neck1/blocks/conv3/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/conv/conv/Conv + /model/neck/neck2/conv/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck2/upsample/ConvTranspose
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/reduce_skip1/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_after_concat/conv/Conv + /model/neck/neck2/reduce_after_concat/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv2/conv/Conv + /model/neck/neck2/blocks/conv2/act/Relu || /model/neck/neck2/blocks/conv1/conv/Conv + /model/neck/neck2/blocks/conv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 216) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 224) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 232) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.3.alpha + (Unnamed Layer* 240) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv3/conv/Conv + /model/neck/neck2/blocks/conv3/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/bbox_stem/seq/conv/Conv + /model/heads/head1/bbox_stem/seq/act/Relu || /model/heads/head1/pose_stem/seq/conv/Conv + /model/heads/head1/pose_stem/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/conv/conv/Conv + /model/neck/neck3/conv/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head1/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head1/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head1/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv2/conv/Conv + /model/neck/neck3/blocks/conv2/act/Relu || /model/neck/neck3/blocks/conv1/conv/Conv + /model/neck/neck3/blocks/conv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/cls_pred/Conv
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_pred/Conv
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape + /model/heads/Transpose
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_pred/Conv
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 271) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 294) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 302) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 310) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv3/conv/Conv + /model/neck/neck3/blocks/conv3/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_stem/seq/conv/Conv + /model/heads/head2/pose_stem/seq/act/Relu || /model/heads/head2/bbox_stem/seq/conv/Conv + /model/heads/head2/bbox_stem/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/conv/conv/Conv + /model/neck/neck4/conv/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head2/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head2/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head2/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv2/conv/Conv + /model/neck/neck4/blocks/conv2/act/Relu || /model/neck/neck4/blocks/conv1/conv/Conv + /model/neck/neck4/blocks/conv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/cls_pred/Conv
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_pred/Conv
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_4 + /model/heads/Transpose_3
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_pred/Conv
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_1
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 341) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_1
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 364) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.2.alpha + (Unnamed Layer* 372) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.3.alpha + (Unnamed Layer* 380) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv3/conv/Conv + /model/neck/neck4/blocks/conv3/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/bbox_stem/seq/conv/Conv + /model/heads/head3/bbox_stem/seq/act/Relu || /model/heads/head3/pose_stem/seq/conv/Conv + /model/heads/head3/pose_stem/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head3/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head3/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head3/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/cls_pred/Conv
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_pred/Conv
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_8 + /model/heads/Transpose_6
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.2/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.2/seq/act/Relu
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_2
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_pred/Conv
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_2
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice_1.../post_process/Reshape_2]}
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] NMS: batched_nms_26
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] DEVICE_TO_SHAPE_HOST: (Unnamed Layer* 459) [NMS]_1_output[DevicetoShapeHostCopy]
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation2]
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice...graph2_/Concat_5]}
+[12/28/2023-12:58:52] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation3]
+[12/28/2023-12:59:03] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +534, GPU +411, now: CPU 1351, GPU 3918 (MiB)
+[12/28/2023-12:59:05] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +82, GPU +80, now: CPU 1433, GPU 3998 (MiB)
+[12/28/2023-12:59:05] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
+[12/28/2023-15:09:20] [I] [TRT] Total Activation Memory: 7964877312
+[12/28/2023-15:09:20] [I] [TRT] Detected 1 inputs and 1 output network tensors.
+[12/28/2023-15:09:38] [I] [TRT] Total Host Persistent Memory: 331680
+[12/28/2023-15:09:38] [I] [TRT] Total Device Persistent Memory: 38912
+[12/28/2023-15:09:38] [I] [TRT] Total Scratch Memory: 134217728
+[12/28/2023-15:09:38] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 88 MiB, GPU 2110 MiB
+[12/28/2023-15:09:38] [I] [TRT] [BlockAssignment] Started assigning block shifts. This will take 176 steps to complete.
+[12/28/2023-15:09:38] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 114.49ms to assign 14 blocks to 176 nodes requiring 147384320 bytes.
+[12/28/2023-15:09:38] [I] [TRT] Total Activation Memory: 147384320
+[12/28/2023-15:09:47] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU -15, now: CPU 1838, GPU 5747 (MiB)
+[12/28/2023-15:09:47] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +53, GPU +64, now: CPU 53, GPU 64 (MiB)
+[12/28/2023-15:09:48] [I] Engine built in 7870.12 sec.
+[12/28/2023-15:09:48] [I] [TRT] Loaded engine size: 54 MiB
+[12/28/2023-15:09:48] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1299, GPU 5509 (MiB)
+[12/28/2023-15:09:48] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +52, now: CPU 0, GPU 52 (MiB)
+[12/28/2023-15:09:48] [I] Engine deserialized in 0.136755 sec.
+[12/28/2023-15:09:48] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1300, GPU 5509 (MiB)
+[12/28/2023-15:09:48] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +140, now: CPU 0, GPU 192 (MiB)
+[12/28/2023-15:09:48] [I] Setting persistentCacheLimit to 0 bytes.
+[12/28/2023-15:09:48] [I] Using random values for input onnx::Cast_0
+[12/28/2023-15:09:48] [I] Created input binding for onnx::Cast_0 with dimensions 1x3x640x640
+[12/28/2023-15:09:48] [I] Using random values for output graph2_flat_predictions
+[12/28/2023-15:09:48] [I] Created output binding for graph2_flat_predictions with dimensions -1x57
+[12/28/2023-15:09:48] [I] Starting inference
+[12/28/2023-15:10:04] [I] Warmup completed 2 queries over 200 ms
+[12/28/2023-15:10:04] [I] Timing trace has 712 queries over 15.0201 s
+[12/28/2023-15:10:04] [I] 
+[12/28/2023-15:10:04] [I] === Trace details ===
+[12/28/2023-15:10:04] [I] Trace averages of 100 runs:
+[12/28/2023-15:10:04] [I] Average on 100 runs - GPU latency: 21.1141 ms - Host latency: 21.2281 ms (enqueue 21.1848 ms)
+[12/28/2023-15:10:04] [I] Average on 100 runs - GPU latency: 21.2938 ms - Host latency: 21.4086 ms (enqueue 21.3535 ms)
+[12/28/2023-15:10:04] [I] Average on 100 runs - GPU latency: 20.5876 ms - Host latency: 20.6987 ms (enqueue 20.679 ms)
+[12/28/2023-15:10:04] [I] Average on 100 runs - GPU latency: 20.9284 ms - Host latency: 21.0399 ms (enqueue 20.9968 ms)
+[12/28/2023-15:10:04] [I] Average on 100 runs - GPU latency: 21.3846 ms - Host latency: 21.5023 ms (enqueue 21.4432 ms)
+[12/28/2023-15:10:04] [I] Average on 100 runs - GPU latency: 20.5315 ms - Host latency: 20.6422 ms (enqueue 20.6192 ms)
+[12/28/2023-15:10:04] [I] Average on 100 runs - GPU latency: 20.7566 ms - Host latency: 20.8657 ms (enqueue 20.8177 ms)
+[12/28/2023-15:10:04] [I] 
+[12/28/2023-15:10:04] [I] === Performance summary ===
+[12/28/2023-15:10:04] [I] Throughput: 47.4032 qps
+[12/28/2023-15:10:04] [I] Latency: min = 19.6377 ms, max = 32.405 ms, mean = 21.0632 ms, median = 20.583 ms, percentile(90%) = 21.897 ms, percentile(95%) = 23.0127 ms, percentile(99%) = 29.6182 ms
+[12/28/2023-15:10:04] [I] Enqueue Time: min = 19.6035 ms, max = 33.8328 ms, mean = 21.0211 ms, median = 20.5366 ms, percentile(90%) = 21.8384 ms, percentile(95%) = 22.998 ms, percentile(99%) = 29.0708 ms
+[12/28/2023-15:10:04] [I] H2D Latency: min = 0.0800781 ms, max = 0.128906 ms, mean = 0.0964459 ms, median = 0.097168 ms, percentile(90%) = 0.0991211 ms, percentile(95%) = 0.0996094 ms, percentile(99%) = 0.110474 ms
+[12/28/2023-15:10:04] [I] GPU Compute Time: min = 19.5264 ms, max = 32.2937 ms, mean = 20.9506 ms, median = 20.4727 ms, percentile(90%) = 21.7739 ms, percentile(95%) = 22.8984 ms, percentile(99%) = 29.5049 ms
+[12/28/2023-15:10:04] [I] D2H Latency: min = 0.00341797 ms, max = 0.0615234 ms, mean = 0.0161761 ms, median = 0.0136719 ms, percentile(90%) = 0.0258789 ms, percentile(95%) = 0.0273438 ms, percentile(99%) = 0.03125 ms
+[12/28/2023-15:10:04] [I] Total Host Walltime: 15.0201 s
+[12/28/2023-15:10:04] [I] Total GPU Compute Time: 14.9168 s
+[12/28/2023-15:10:04] [I] Explanations of the performance metrics are printed in the verbose logs.
+[12/28/2023-15:10:04] [I] 
+&&&& PASSED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp32.onnx --best --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp32.onnx.best.engine

yolo_nas_pose_l_fp32.onnx.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ae49ee96e19ad3d8bfede2728e2c7fb331aa5a1d99fc7b5e139b10ec687299
+size 219687473

yolo_nas_pose_l_fp32.onnx.engine.err

@@ -0,0 +1,237 @@
+[12/28/2023-11:29:23] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-11:29:23] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-11:30:52] [W] [TRT] Tactic Device request: 4720MB Available: 2387MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:30:52] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4720 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:30:53] [W] [TRT] Tactic Device request: 4720MB Available: 2388MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:30:53] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4720 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:30:54] [W] [TRT] Tactic Device request: 4720MB Available: 2389MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:30:54] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4720 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:30:59] [W] [TRT] Tactic Device request: 4711MB Available: 2388MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:30:59] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:31:00] [W] [TRT] Tactic Device request: 4711MB Available: 2388MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:31:00] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:31:00] [W] [TRT] Tactic Device request: 4711MB Available: 2389MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:31:00] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:32:39] [W] [TRT] Tactic Device request: 4711MB Available: 2349MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:32:39] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:32:39] [W] [TRT] Tactic Device request: 4711MB Available: 2348MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:32:39] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:32:39] [W] [TRT] Tactic Device request: 4711MB Available: 2349MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:32:39] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:32:51] [W] [TRT] Tactic Device request: 6275MB Available: 2347MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:32:51] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:32:51] [W] [TRT] Tactic Device request: 6275MB Available: 2348MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:32:51] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6275 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:32:51] [W] [TRT] Tactic Device request: 6275MB Available: 2350MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:32:51] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:35:14] [W] [TRT] Tactic Device request: 7056MB Available: 2331MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:35:14] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:35:14] [W] [TRT] Tactic Device request: 7056MB Available: 2330MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:35:14] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 7056 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:35:15] [W] [TRT] Tactic Device request: 7056MB Available: 2330MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:35:15] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:35:27] [W] [TRT] Tactic Device request: 6354MB Available: 2331MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:35:27] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:35:27] [W] [TRT] Tactic Device request: 6354MB Available: 2331MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:35:27] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6354 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:35:27] [W] [TRT] Tactic Device request: 6354MB Available: 2331MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:35:27] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:31] [W] [TRT] Tactic Device request: 2394MB Available: 2273MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:31] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2394 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:31] [W] [TRT] Tactic Device request: 2394MB Available: 2273MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:31] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2394 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:31] [W] [TRT] Tactic Device request: 2394MB Available: 2273MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:31] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2394 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:32] [W] [TRT] Tactic Device request: 2392MB Available: 2272MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:32] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:32] [W] [TRT] Tactic Device request: 2392MB Available: 2272MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:32] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2392 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:32] [W] [TRT] Tactic Device request: 2392MB Available: 2272MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:32] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:41] [W] [TRT] Tactic Device request: 6540MB Available: 2263MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:41] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6540 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:42] [W] [TRT] Tactic Device request: 6540MB Available: 2262MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:42] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6540 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:42] [W] [TRT] Tactic Device request: 6540MB Available: 2262MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:42] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6540 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:46] [W] [TRT] Tactic Device request: 2191MB Available: 2163MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:46] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2191 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:47] [W] [TRT] Tactic Device request: 2191MB Available: 2160MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:47] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2191 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:51] [W] [TRT] Tactic Device request: 2190MB Available: 2161MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:51] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:52] [W] [TRT] Tactic Device request: 2190MB Available: 2161MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:52] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:38:53] [W] [TRT] Tactic Device request: 2190MB Available: 2161MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:38:53] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:40:32] [W] [TRT] Tactic Device request: 2457MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:40:32] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:40:32] [W] [TRT] Tactic Device request: 2457MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:40:32] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2457 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:40:32] [W] [TRT] Tactic Device request: 2457MB Available: 2131MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:40:32] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:40:46] [W] [TRT] Tactic Device request: 3587MB Available: 2158MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:40:46] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:40:46] [W] [TRT] Tactic Device request: 3587MB Available: 2158MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:40:46] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3587 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:40:46] [W] [TRT] Tactic Device request: 3587MB Available: 2158MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:40:46] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:43:23] [W] [TRT] Tactic Device request: 3556MB Available: 2179MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:43:23] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:43:23] [W] [TRT] Tactic Device request: 3556MB Available: 2179MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:43:23] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3556 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:43:23] [W] [TRT] Tactic Device request: 3556MB Available: 2179MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:43:23] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:43:24] [W] [TRT] Tactic Device request: 3140MB Available: 2178MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:43:24] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3140 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:43:24] [W] [TRT] Tactic Device request: 3140MB Available: 2178MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:43:24] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3140 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:43:24] [W] [TRT] Tactic Device request: 3140MB Available: 2178MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:43:24] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3140 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:45:43] [W] [TRT] Tactic Device request: 3161MB Available: 2140MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:45:43] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3161 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:45:43] [W] [TRT] Tactic Device request: 3161MB Available: 2140MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:45:43] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3161 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:45:43] [W] [TRT] Tactic Device request: 3161MB Available: 2140MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:45:43] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3161 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:45:46] [W] [TRT] Tactic Device request: 4189MB Available: 2138MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:45:46] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4189 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:45:47] [W] [TRT] Tactic Device request: 4189MB Available: 2138MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:45:47] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4189 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:45:47] [W] [TRT] Tactic Device request: 4189MB Available: 2140MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:45:47] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4189 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:45:51] [W] [TRT] Tactic Device request: 4186MB Available: 2139MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:45:51] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4186 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:45:52] [W] [TRT] Tactic Device request: 4186MB Available: 2139MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:45:52] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4186 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:45:52] [W] [TRT] Tactic Device request: 4186MB Available: 2138MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:45:52] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4186 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:48:34] [W] [TRT] Tactic Device request: 4764MB Available: 2088MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:48:34] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4764 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:48:34] [W] [TRT] Tactic Device request: 4764MB Available: 2088MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:48:34] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4764 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:48:34] [W] [TRT] Tactic Device request: 4764MB Available: 2088MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:48:34] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4764 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:48:39] [W] [TRT] Tactic Device request: 4244MB Available: 2088MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:48:39] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4244 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:48:40] [W] [TRT] Tactic Device request: 4244MB Available: 2081MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:48:40] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4244 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:48:41] [W] [TRT] Tactic Device request: 4244MB Available: 2080MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:48:41] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4244 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:48:46] [W] [TRT] Tactic Device request: 4241MB Available: 2082MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:48:46] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4241 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:48:47] [W] [TRT] Tactic Device request: 4241MB Available: 2080MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:48:47] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4241 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:48:48] [W] [TRT] Tactic Device request: 4241MB Available: 2080MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:48:48] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4241 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:51:58] [W] [TRT] Tactic Device request: 3270MB Available: 2043MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:51:58] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3270 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:51:58] [W] [TRT] Tactic Device request: 3270MB Available: 2043MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:51:58] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3270 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:51:58] [W] [TRT] Tactic Device request: 3270MB Available: 2043MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:51:58] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3270 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:01] [W] [TRT] Tactic Device request: 4377MB Available: 2039MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:52:01] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4377 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:01] [W] [TRT] Tactic Device request: 2185MB Available: 2039MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:52:01] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2185 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:01] [W] [TRT] Tactic Device request: 4377MB Available: 2039MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:52:01] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4377 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:01] [W] [TRT] Tactic Device request: 2185MB Available: 2039MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:52:01] [W] [TRT] Skipping tactic 10 due to insufficient memory on requested size of 2185 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:02] [W] [TRT] Tactic Device request: 4377MB Available: 2039MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:52:02] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4377 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:02] [W] [TRT] Tactic Device request: 2185MB Available: 2038MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:52:02] [W] [TRT] Skipping tactic 16 due to insufficient memory on requested size of 2185 detected for tactic 0x0000000000000075.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:09] [W] [TRT] Tactic Device request: 4376MB Available: 2038MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:52:09] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4376 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:09] [W] [TRT] Tactic Device request: 2184MB Available: 2038MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:52:09] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2184 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:09] [W] [TRT] Tactic Device request: 4376MB Available: 2038MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:52:09] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4376 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:09] [W] [TRT] Tactic Device request: 2184MB Available: 2038MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:52:09] [W] [TRT] Skipping tactic 10 due to insufficient memory on requested size of 2184 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:09] [W] [TRT] Tactic Device request: 4376MB Available: 2037MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:52:09] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4376 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:09] [W] [TRT] Tactic Device request: 2184MB Available: 2038MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:52:09] [W] [TRT] Skipping tactic 16 due to insufficient memory on requested size of 2184 detected for tactic 0x0000000000000075.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:52:51] [W] * Throughput may be bound by Enqueue Time rather than GPU Compute and the GPU may be under-utilized.
+[12/28/2023-11:52:51] [W]   If not already in use, --useCudaGraph (utilize CUDA graphs where possible) may increase the throughput.
+[12/28/2023-11:52:51] [W] * GPU compute time is unstable, with coefficient of variance = 4.81745%.
+[12/28/2023-11:52:51] [W]   If not already in use, locking GPU clock frequency or adding --useSpinWait may improve the stability.

yolo_nas_pose_l_fp32.onnx.engine.log

@@ -0,0 +1,326 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp32.onnx --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp32.onnx.engine
+[12/28/2023-11:29:16] [I] === Model Options ===
+[12/28/2023-11:29:16] [I] Format: ONNX
+[12/28/2023-11:29:16] [I] Model: yolo_nas_pose_l_fp32.onnx
+[12/28/2023-11:29:16] [I] Output:
+[12/28/2023-11:29:16] [I] === Build Options ===
+[12/28/2023-11:29:16] [I] Max batch: explicit batch
+[12/28/2023-11:29:16] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-11:29:16] [I] minTiming: 1
+[12/28/2023-11:29:16] [I] avgTiming: 8
+[12/28/2023-11:29:16] [I] Precision: FP32
+[12/28/2023-11:29:16] [I] LayerPrecisions: 
+[12/28/2023-11:29:16] [I] Calibration: 
+[12/28/2023-11:29:16] [I] Refit: Disabled
+[12/28/2023-11:29:16] [I] Sparsity: Disabled
+[12/28/2023-11:29:16] [I] Safe mode: Disabled
+[12/28/2023-11:29:16] [I] DirectIO mode: Disabled
+[12/28/2023-11:29:16] [I] Restricted mode: Disabled
+[12/28/2023-11:29:16] [I] Build only: Disabled
+[12/28/2023-11:29:16] [I] Save engine: yolo_nas_pose_l_fp32.onnx.engine
+[12/28/2023-11:29:16] [I] Load engine: 
+[12/28/2023-11:29:16] [I] Profiling verbosity: 0
+[12/28/2023-11:29:16] [I] Tactic sources: Using default tactic sources
+[12/28/2023-11:29:16] [I] timingCacheMode: local
+[12/28/2023-11:29:16] [I] timingCacheFile: 
+[12/28/2023-11:29:16] [I] Heuristic: Disabled
+[12/28/2023-11:29:16] [I] Preview Features: Use default preview flags.
+[12/28/2023-11:29:16] [I] Input(s)s format: fp32:CHW
+[12/28/2023-11:29:16] [I] Output(s)s format: fp32:CHW
+[12/28/2023-11:29:16] [I] Input build shapes: model
+[12/28/2023-11:29:16] [I] Input calibration shapes: model
+[12/28/2023-11:29:16] [I] === System Options ===
+[12/28/2023-11:29:16] [I] Device: 0
+[12/28/2023-11:29:16] [I] DLACore: 
+[12/28/2023-11:29:16] [I] Plugins:
+[12/28/2023-11:29:16] [I] === Inference Options ===
+[12/28/2023-11:29:16] [I] Batch: Explicit
+[12/28/2023-11:29:16] [I] Input inference shapes: model
+[12/28/2023-11:29:16] [I] Iterations: 10
+[12/28/2023-11:29:16] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-11:29:16] [I] Sleep time: 0ms
+[12/28/2023-11:29:16] [I] Idle time: 0ms
+[12/28/2023-11:29:16] [I] Streams: 1
+[12/28/2023-11:29:16] [I] ExposeDMA: Disabled
+[12/28/2023-11:29:16] [I] Data transfers: Enabled
+[12/28/2023-11:29:16] [I] Spin-wait: Disabled
+[12/28/2023-11:29:16] [I] Multithreading: Disabled
+[12/28/2023-11:29:16] [I] CUDA Graph: Disabled
+[12/28/2023-11:29:16] [I] Separate profiling: Disabled
+[12/28/2023-11:29:16] [I] Time Deserialize: Disabled
+[12/28/2023-11:29:16] [I] Time Refit: Disabled
+[12/28/2023-11:29:16] [I] NVTX verbosity: 0
+[12/28/2023-11:29:16] [I] Persistent Cache Ratio: 0
+[12/28/2023-11:29:16] [I] Inputs:
+[12/28/2023-11:29:16] [I] === Reporting Options ===
+[12/28/2023-11:29:16] [I] Verbose: Disabled
+[12/28/2023-11:29:16] [I] Averages: 100 inferences
+[12/28/2023-11:29:16] [I] Percentiles: 90,95,99
+[12/28/2023-11:29:16] [I] Dump refittable layers:Disabled
+[12/28/2023-11:29:16] [I] Dump output: Disabled
+[12/28/2023-11:29:16] [I] Profile: Disabled
+[12/28/2023-11:29:16] [I] Export timing to JSON file: 
+[12/28/2023-11:29:16] [I] Export output to JSON file: 
+[12/28/2023-11:29:16] [I] Export profile to JSON file: 
+[12/28/2023-11:29:16] [I] 
+[12/28/2023-11:29:16] [I] === Device Information ===
+[12/28/2023-11:29:16] [I] Selected Device: Orin
+[12/28/2023-11:29:16] [I] Compute Capability: 8.7
+[12/28/2023-11:29:16] [I] SMs: 8
+[12/28/2023-11:29:16] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-11:29:16] [I] Device Global Memory: 7471 MiB
+[12/28/2023-11:29:16] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-11:29:16] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-11:29:16] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-11:29:16] [I] 
+[12/28/2023-11:29:16] [I] TensorRT version: 8.5.2
+[12/28/2023-11:29:17] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 3132 (MiB)
+[12/28/2023-11:29:20] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +424, now: CPU 574, GPU 3573 (MiB)
+[12/28/2023-11:29:20] [I] Start parsing network model
+[12/28/2023-11:29:23] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-11:29:23] [I] [TRT] Input filename:   yolo_nas_pose_l_fp32.onnx
+[12/28/2023-11:29:23] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-11:29:23] [I] [TRT] Opset version:    17
+[12/28/2023-11:29:23] [I] [TRT] Producer name:    pytorch
+[12/28/2023-11:29:23] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-11:29:23] [I] [TRT] Domain:           
+[12/28/2023-11:29:23] [I] [TRT] Model version:    0
+[12/28/2023-11:29:23] [I] [TRT] Doc string:       
+[12/28/2023-11:29:23] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-11:29:23] [I] Finish parsing network model
+[12/28/2023-11:29:23] [I] [TRT] ---------- Layers Running on DLA ----------
+[12/28/2023-11:29:23] [I] [TRT] ---------- Layers Running on GPU ----------
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation1]
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/pre_process/pre_process.0/Cast.../pre_process/pre_process.2/Mul]}
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 455) [Constant]
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 456) [Constant]
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 457) [Constant]
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stem/conv/rbr_reparam/Conv + /model/backbone/stem/conv/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/downsample/rbr_reparam/Conv + /model/backbone/stage1/downsample/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv2/conv/Conv + /model/backbone/stage1/blocks/conv2/act/Relu || /model/backbone/stage1/blocks/conv1/conv/Conv + /model/backbone/stage1/blocks/conv1/act/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 15) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 23) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv3/conv/Conv + /model/backbone/stage1/blocks/conv3/act/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_skip2/conv/Conv + /model/neck/neck2/reduce_skip2/act/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/downsample/rbr_reparam/Conv + /model/backbone/stage2/downsample/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/downsample/conv/Conv + /model/neck/neck2/downsample/act/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv2/conv/Conv + /model/backbone/stage2/blocks/conv2/act/Relu || /model/backbone/stage2/blocks/conv1/conv/Conv + /model/backbone/stage2/blocks/conv1/act/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 44) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 52) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 60) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-11:29:23] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv3/conv/Conv + /model/backbone/stage2/blocks/conv3/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip2/conv/Conv + /model/neck/neck1/reduce_skip2/act/Relu || /model/neck/neck2/reduce_skip1/conv/Conv + /model/neck/neck2/reduce_skip1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/downsample/rbr_reparam/Conv + /model/backbone/stage3/downsample/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/downsample/conv/Conv + /model/neck/neck1/downsample/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv2/conv/Conv + /model/backbone/stage3/blocks/conv2/act/Relu || /model/backbone/stage3/blocks/conv1/conv/Conv + /model/backbone/stage3/blocks/conv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 83) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 91) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 99) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 107) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.4.alpha + (Unnamed Layer* 115) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv3/conv/Conv + /model/backbone/stage3/blocks/conv3/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip1/conv/Conv + /model/neck/neck1/reduce_skip1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/downsample/rbr_reparam/Conv + /model/backbone/stage4/downsample/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv2/conv/Conv + /model/backbone/stage4/blocks/conv2/act/Relu || /model/backbone/stage4/blocks/conv1/conv/Conv + /model/backbone/stage4/blocks/conv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 134) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 142) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv3/conv/Conv + /model/backbone/stage4/blocks/conv3/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv1/conv/Conv + /model/backbone/context_module/cv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.2/MaxPool
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.1/MaxPool
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.0/MaxPool
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/backbone/context_module/cv1/act/Relu_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv2/conv/Conv + /model/backbone/context_module/cv2/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/conv/conv/Conv + /model/neck/neck1/conv/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck1/upsample/ConvTranspose
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_after_concat/conv/Conv + /model/neck/neck1/reduce_after_concat/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv2/conv/Conv + /model/neck/neck1/blocks/conv2/act/Relu || /model/neck/neck1/blocks/conv1/conv/Conv + /model/neck/neck1/blocks/conv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 171) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 179) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.2.alpha + (Unnamed Layer* 187) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.3.alpha + (Unnamed Layer* 195) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv3/conv/Conv + /model/neck/neck1/blocks/conv3/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/conv/conv/Conv + /model/neck/neck2/conv/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck2/upsample/ConvTranspose
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/reduce_skip1/act/Relu_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_after_concat/conv/Conv + /model/neck/neck2/reduce_after_concat/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv2/conv/Conv + /model/neck/neck2/blocks/conv2/act/Relu || /model/neck/neck2/blocks/conv1/conv/Conv + /model/neck/neck2/blocks/conv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 216) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 224) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 232) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.3.alpha + (Unnamed Layer* 240) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv3/conv/Conv + /model/neck/neck2/blocks/conv3/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/bbox_stem/seq/conv/Conv + /model/heads/head1/bbox_stem/seq/act/Relu || /model/heads/head1/pose_stem/seq/conv/Conv + /model/heads/head1/pose_stem/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/conv/conv/Conv + /model/neck/neck3/conv/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head1/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head1/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head1/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv2/conv/Conv + /model/neck/neck3/blocks/conv2/act/Relu || /model/neck/neck3/blocks/conv1/conv/Conv + /model/neck/neck3/blocks/conv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/cls_pred/Conv
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_pred/Conv
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape + /model/heads/Transpose
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_pred/Conv
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 271) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 294) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 302) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 310) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv3/conv/Conv + /model/neck/neck3/blocks/conv3/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_stem/seq/conv/Conv + /model/heads/head2/pose_stem/seq/act/Relu || /model/heads/head2/bbox_stem/seq/conv/Conv + /model/heads/head2/bbox_stem/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/conv/conv/Conv + /model/neck/neck4/conv/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head2/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head2/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head2/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv2/conv/Conv + /model/neck/neck4/blocks/conv2/act/Relu || /model/neck/neck4/blocks/conv1/conv/Conv + /model/neck/neck4/blocks/conv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/cls_pred/Conv
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_pred/Conv
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_4 + /model/heads/Transpose_3
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_pred/Conv
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_1
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 341) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_1
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 364) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.2.alpha + (Unnamed Layer* 372) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.3.alpha + (Unnamed Layer* 380) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv3/conv/Conv + /model/neck/neck4/blocks/conv3/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/bbox_stem/seq/conv/Conv + /model/heads/head3/bbox_stem/seq/act/Relu || /model/heads/head3/pose_stem/seq/conv/Conv + /model/heads/head3/pose_stem/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head3/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head3/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head3/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/cls_pred/Conv
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_pred/Conv
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_8 + /model/heads/Transpose_6
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.2/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.2/seq/act/Relu
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_2
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_pred/Conv
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_2
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice_1.../post_process/Reshape_2]}
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] NMS: batched_nms_26
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] DEVICE_TO_SHAPE_HOST: (Unnamed Layer* 459) [NMS]_1_output[DevicetoShapeHostCopy]
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation2]
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice...graph2_/Concat_5]}
+[12/28/2023-11:29:24] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation3]
+[12/28/2023-11:29:25] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +534, GPU +763, now: CPU 1350, GPU 4631 (MiB)
+[12/28/2023-11:29:25] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +83, GPU +131, now: CPU 1433, GPU 4762 (MiB)
+[12/28/2023-11:29:25] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
+[12/28/2023-11:52:24] [I] [TRT] Total Activation Memory: 8308511744
+[12/28/2023-11:52:24] [I] [TRT] Detected 1 inputs and 1 output network tensors.
+[12/28/2023-11:52:32] [I] [TRT] Total Host Persistent Memory: 380944
+[12/28/2023-11:52:32] [I] [TRT] Total Device Persistent Memory: 656384
+[12/28/2023-11:52:32] [I] [TRT] Total Scratch Memory: 134217728
+[12/28/2023-11:52:32] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 49 MiB, GPU 2207 MiB
+[12/28/2023-11:52:32] [I] [TRT] [BlockAssignment] Started assigning block shifts. This will take 216 steps to complete.
+[12/28/2023-11:52:32] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 108.365ms to assign 15 blocks to 216 nodes requiring 188319232 bytes.
+[12/28/2023-11:52:32] [I] [TRT] Total Activation Memory: 188319232
+[12/28/2023-11:52:34] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1778, GPU 5584 (MiB)
+[12/28/2023-11:52:34] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +31, GPU +256, now: CPU 31, GPU 256 (MiB)
+[12/28/2023-11:52:35] [I] Engine built in 1398.12 sec.
+[12/28/2023-11:52:35] [I] [TRT] Loaded engine size: 209 MiB
+[12/28/2023-11:52:36] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1451, GPU 4904 (MiB)
+[12/28/2023-11:52:36] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +208, now: CPU 0, GPU 208 (MiB)
+[12/28/2023-11:52:36] [I] Engine deserialized in 0.328264 sec.
+[12/28/2023-11:52:36] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1451, GPU 4904 (MiB)
+[12/28/2023-11:52:36] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +180, now: CPU 0, GPU 388 (MiB)
+[12/28/2023-11:52:36] [I] Setting persistentCacheLimit to 0 bytes.
+[12/28/2023-11:52:36] [I] Using random values for input onnx::Cast_0
+[12/28/2023-11:52:36] [I] Created input binding for onnx::Cast_0 with dimensions 1x3x640x640
+[12/28/2023-11:52:36] [I] Using random values for output graph2_flat_predictions
+[12/28/2023-11:52:36] [I] Created output binding for graph2_flat_predictions with dimensions -1x57
+[12/28/2023-11:52:36] [I] Starting inference
+[12/28/2023-11:52:51] [I] Warmup completed 3 queries over 200 ms
+[12/28/2023-11:52:51] [I] Timing trace has 228 queries over 15.134 s
+[12/28/2023-11:52:51] [I] 
+[12/28/2023-11:52:51] [I] === Trace details ===
+[12/28/2023-11:52:51] [I] Trace averages of 100 runs:
+[12/28/2023-11:52:51] [I] Average on 100 runs - GPU latency: 66.5633 ms - Host latency: 66.6799 ms (enqueue 66.6144 ms)
+[12/28/2023-11:52:51] [I] Average on 100 runs - GPU latency: 65.9454 ms - Host latency: 66.065 ms (enqueue 66.0061 ms)
+[12/28/2023-11:52:51] [I] 
+[12/28/2023-11:52:51] [I] === Performance summary ===
+[12/28/2023-11:52:51] [I] Throughput: 15.0654 qps
+[12/28/2023-11:52:51] [I] Latency: min = 63.8037 ms, max = 84.0011 ms, mean = 66.3393 ms, median = 65.521 ms, percentile(90%) = 67.4297 ms, percentile(95%) = 76.3467 ms, percentile(99%) = 78.6501 ms
+[12/28/2023-11:52:51] [I] Enqueue Time: min = 63.7715 ms, max = 83.9532 ms, mean = 66.2756 ms, median = 65.4399 ms, percentile(90%) = 68.3887 ms, percentile(95%) = 76.9697 ms, percentile(99%) = 78.6002 ms
+[12/28/2023-11:52:51] [I] H2D Latency: min = 0.081543 ms, max = 0.12793 ms, mean = 0.0942483 ms, median = 0.0947266 ms, percentile(90%) = 0.0976562 ms, percentile(95%) = 0.0986328 ms, percentile(99%) = 0.112305 ms
+[12/28/2023-11:52:51] [I] GPU Compute Time: min = 63.6914 ms, max = 83.8763 ms, mean = 66.222 ms, median = 65.4058 ms, percentile(90%) = 67.313 ms, percentile(95%) = 76.2305 ms, percentile(99%) = 78.5333 ms
+[12/28/2023-11:52:51] [I] D2H Latency: min = 0.00390625 ms, max = 0.0869141 ms, mean = 0.023145 ms, median = 0.0244141 ms, percentile(90%) = 0.0336914 ms, percentile(95%) = 0.0390625 ms, percentile(99%) = 0.0546875 ms
+[12/28/2023-11:52:51] [I] Total Host Walltime: 15.134 s
+[12/28/2023-11:52:51] [I] Total GPU Compute Time: 15.0986 s
+[12/28/2023-11:52:51] [I] Explanations of the performance metrics are printed in the verbose logs.
+[12/28/2023-11:52:51] [I] 
+&&&& PASSED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp32.onnx --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp32.onnx.engine

yolo_nas_pose_l_fp32.onnx.fp16.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3274fec20ea219c10bcdf044022eedcd2ced07cc929ad0b5f08c625d5fdf12b4
+size 110783531

yolo_nas_pose_l_fp32.onnx.fp16.engine.err

@@ -0,0 +1,401 @@
+[12/28/2023-11:53:03] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-11:53:03] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-11:58:20] [W] [TRT] Tactic Device request: 4720MB Available: 2406MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:58:20] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4720 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:58:20] [W] [TRT] Tactic Device request: 4720MB Available: 2407MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:58:20] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4720 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:58:21] [W] [TRT] Tactic Device request: 4720MB Available: 2407MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:58:21] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4720 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:58:27] [W] [TRT] Tactic Device request: 4706MB Available: 2408MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:58:27] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4706 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:58:27] [W] [TRT] Tactic Device request: 4706MB Available: 2408MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:58:28] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4706 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:58:30] [W] [TRT] Tactic Device request: 4711MB Available: 2408MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:58:30] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:58:31] [W] [TRT] Tactic Device request: 4711MB Available: 2407MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:58:31] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:58:32] [W] [TRT] Tactic Device request: 4711MB Available: 2407MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:58:32] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:58:37] [W] [TRT] Tactic Device request: 4702MB Available: 2407MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:58:37] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4702 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-11:58:38] [W] [TRT] Tactic Device request: 4702MB Available: 2407MB. Device memory is insufficient to use tactic.
+[12/28/2023-11:58:38] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4702 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:03:21] [W] [TRT] Tactic Device request: 4711MB Available: 2283MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:03:21] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:03:21] [W] [TRT] Tactic Device request: 4711MB Available: 2282MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:03:21] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:03:21] [W] [TRT] Tactic Device request: 4711MB Available: 2282MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:03:21] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:03:23] [W] [TRT] Tactic Device request: 4701MB Available: 2281MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:03:23] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4701 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:03:23] [W] [TRT] Tactic Device request: 4701MB Available: 2281MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:03:23] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4701 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:03:40] [W] [TRT] Tactic Device request: 6275MB Available: 2278MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:03:41] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:03:41] [W] [TRT] Tactic Device request: 6275MB Available: 2277MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:03:41] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6275 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:03:41] [W] [TRT] Tactic Device request: 6275MB Available: 2278MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:03:41] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:03:43] [W] [TRT] Tactic Device request: 6270MB Available: 2276MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:03:43] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6270 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:03:43] [W] [TRT] Tactic Device request: 6270MB Available: 2276MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:03:43] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6270 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:10:19] [W] [TRT] Tactic Device request: 7056MB Available: 2319MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:10:19] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:10:19] [W] [TRT] Tactic Device request: 7056MB Available: 2319MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:10:19] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 7056 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:10:19] [W] [TRT] Tactic Device request: 7056MB Available: 2319MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:10:19] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:10:21] [W] [TRT] Tactic Device request: 7050MB Available: 2320MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:10:21] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7050 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:10:21] [W] [TRT] Tactic Device request: 7050MB Available: 2320MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:10:21] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 7050 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:10:37] [W] [TRT] Tactic Device request: 6354MB Available: 2321MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:10:37] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:10:38] [W] [TRT] Tactic Device request: 6354MB Available: 2320MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:10:38] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6354 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:10:38] [W] [TRT] Tactic Device request: 6354MB Available: 2320MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:10:38] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:10:39] [W] [TRT] Tactic Device request: 6351MB Available: 2320MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:10:39] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6351 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:10:39] [W] [TRT] Tactic Device request: 6351MB Available: 2320MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:10:39] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6351 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:26] [W] [TRT] Tactic Device request: 2394MB Available: 2151MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:26] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2394 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:26] [W] [TRT] Tactic Device request: 2394MB Available: 2151MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:26] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2394 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:26] [W] [TRT] Tactic Device request: 2394MB Available: 2151MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:26] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2394 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:27] [W] [TRT] Tactic Device request: 2392MB Available: 2151MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:27] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:27] [W] [TRT] Tactic Device request: 2392MB Available: 2150MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:27] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2392 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:27] [W] [TRT] Tactic Device request: 2392MB Available: 2150MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:27] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:28] [W] [TRT] Tactic Device request: 2391MB Available: 2150MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:28] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2391 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:28] [W] [TRT] Tactic Device request: 2391MB Available: 2150MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:28] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2391 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:28] [W] [TRT] Tactic Device request: 2390MB Available: 2150MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:28] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2390 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:29] [W] [TRT] Tactic Device request: 2390MB Available: 2150MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:29] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2390 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:43] [W] [TRT] Tactic Device request: 6540MB Available: 2123MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:43] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6540 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:43] [W] [TRT] Tactic Device request: 6540MB Available: 2122MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:43] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6540 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:43] [W] [TRT] Tactic Device request: 6540MB Available: 2122MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:43] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6540 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:45] [W] [TRT] Tactic Device request: 6538MB Available: 2121MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:45] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6538 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:45] [W] [TRT] Tactic Device request: 6538MB Available: 2122MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:45] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6538 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:47] [W] [TRT] Tactic Device request: 2191MB Available: 2122MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:47] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2191 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:48] [W] [TRT] Tactic Device request: 2191MB Available: 2123MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:48] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2191 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:49] [W] [TRT] Tactic Device request: 2191MB Available: 2122MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:49] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2191 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:52] [W] [TRT] Tactic Device request: 2190MB Available: 2123MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:52] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:53] [W] [TRT] Tactic Device request: 2190MB Available: 2123MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:53] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:56] [W] [TRT] Tactic Device request: 2190MB Available: 2128MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:56] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:57] [W] [TRT] Tactic Device request: 2190MB Available: 2123MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:57] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:19:58] [W] [TRT] Tactic Device request: 2190MB Available: 2122MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:19:58] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:20:02] [W] [TRT] Tactic Device request: 2190MB Available: 2125MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:20:02] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:20:02] [W] [TRT] Tactic Device request: 2190MB Available: 2122MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:20:02] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:24:51] [W] [TRT] Tactic Device request: 2457MB Available: 2244MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:24:52] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:24:52] [W] [TRT] Tactic Device request: 2457MB Available: 2244MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:24:52] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2457 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:24:52] [W] [TRT] Tactic Device request: 2457MB Available: 2244MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:24:52] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:24:53] [W] [TRT] Tactic Device request: 2456MB Available: 2245MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:24:53] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2456 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:24:53] [W] [TRT] Tactic Device request: 2456MB Available: 2245MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:24:53] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2456 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:25:14] [W] [TRT] Tactic Device request: 3587MB Available: 2175MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:25:14] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:25:14] [W] [TRT] Tactic Device request: 3587MB Available: 2176MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:25:14] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3587 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:25:14] [W] [TRT] Tactic Device request: 3587MB Available: 2176MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:25:15] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:25:16] [W] [TRT] Tactic Device request: 3585MB Available: 2176MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:25:16] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3585 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:25:16] [W] [TRT] Tactic Device request: 3585MB Available: 2176MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:25:16] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3585 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:32:54] [W] [TRT] Tactic Device request: 3556MB Available: 2050MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:32:54] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:32:54] [W] [TRT] Tactic Device request: 3556MB Available: 2051MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:32:54] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3556 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:32:54] [W] [TRT] Tactic Device request: 3556MB Available: 2049MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:32:54] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:32:55] [W] [TRT] Tactic Device request: 3551MB Available: 2050MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:32:55] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3551 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:32:55] [W] [TRT] Tactic Device request: 3551MB Available: 2050MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:32:55] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3551 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:32:56] [W] [TRT] Tactic Device request: 3140MB Available: 2051MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:32:56] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3140 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:32:56] [W] [TRT] Tactic Device request: 3140MB Available: 2050MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:32:56] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3140 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:32:56] [W] [TRT] Tactic Device request: 3140MB Available: 2050MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:32:56] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3140 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:32:57] [W] [TRT] Tactic Device request: 3136MB Available: 2051MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:32:57] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3136 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:32:57] [W] [TRT] Tactic Device request: 3136MB Available: 2051MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:32:57] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3136 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:09] [W] [TRT] Tactic Device request: 3161MB Available: 2255MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:09] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3161 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:09] [W] [TRT] Tactic Device request: 3161MB Available: 2255MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:09] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3161 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:09] [W] [TRT] Tactic Device request: 3161MB Available: 2255MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:09] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3161 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:10] [W] [TRT] Tactic Device request: 3156MB Available: 2253MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:10] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3156 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:10] [W] [TRT] Tactic Device request: 3156MB Available: 2254MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:10] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3156 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:14] [W] [TRT] Tactic Device request: 4189MB Available: 2253MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:14] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4189 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:15] [W] [TRT] Tactic Device request: 4189MB Available: 2253MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:15] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4189 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:15] [W] [TRT] Tactic Device request: 4189MB Available: 2254MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:15] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4189 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:19] [W] [TRT] Tactic Device request: 4183MB Available: 2255MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:20] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4183 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:20] [W] [TRT] Tactic Device request: 4183MB Available: 2255MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:20] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4183 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:22] [W] [TRT] Tactic Device request: 4186MB Available: 2255MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:22] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4186 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:22] [W] [TRT] Tactic Device request: 4186MB Available: 2254MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:22] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4186 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:23] [W] [TRT] Tactic Device request: 4186MB Available: 2254MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:23] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4186 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:27] [W] [TRT] Tactic Device request: 4182MB Available: 2254MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:27] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4182 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:40:27] [W] [TRT] Tactic Device request: 4182MB Available: 2253MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:40:27] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4182 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:15] [W] [TRT] Tactic Device request: 4764MB Available: 2271MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:15] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4764 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:15] [W] [TRT] Tactic Device request: 4764MB Available: 2271MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:15] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4764 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:15] [W] [TRT] Tactic Device request: 4764MB Available: 2269MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:15] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4764 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:17] [W] [TRT] Tactic Device request: 4761MB Available: 2268MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:17] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4761 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:17] [W] [TRT] Tactic Device request: 4761MB Available: 2265MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:17] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4761 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:23] [W] [TRT] Tactic Device request: 4244MB Available: 2235MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:23] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4244 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:24] [W] [TRT] Tactic Device request: 4244MB Available: 1911MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:24] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4244 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:24] [W] [TRT] Tactic Device request: 4244MB Available: 1909MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:25] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4244 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:29] [W] [TRT] Tactic Device request: 4240MB Available: 1905MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:29] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4240 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:30] [W] [TRT] Tactic Device request: 4240MB Available: 1896MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:30] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4240 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:33] [W] [TRT] Tactic Device request: 4241MB Available: 1892MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:33] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4241 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:34] [W] [TRT] Tactic Device request: 4241MB Available: 1864MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:34] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4241 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:35] [W] [TRT] Tactic Device request: 4241MB Available: 1860MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:35] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4241 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:39] [W] [TRT] Tactic Device request: 4239MB Available: 1857MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:39] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4239 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:48:40] [W] [TRT] Tactic Device request: 4239MB Available: 1845MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:48:40] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4239 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:07] [W] [TRT] Tactic Device request: 3270MB Available: 1684MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:07] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3270 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:07] [W] [TRT] Tactic Device request: 3270MB Available: 1684MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:07] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3270 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:07] [W] [TRT] Tactic Device request: 3270MB Available: 1684MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:07] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3270 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:08] [W] [TRT] Tactic Device request: 3269MB Available: 1684MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:08] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3269 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:09] [W] [TRT] Tactic Device request: 3269MB Available: 1684MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:09] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3269 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:11] [W] [TRT] Tactic Device request: 4377MB Available: 1680MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:11] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4377 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:11] [W] [TRT] Tactic Device request: 2185MB Available: 1680MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:11] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2185 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:11] [W] [TRT] Tactic Device request: 4377MB Available: 1680MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:11] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4377 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:11] [W] [TRT] Tactic Device request: 2185MB Available: 1680MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:11] [W] [TRT] Skipping tactic 10 due to insufficient memory on requested size of 2185 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:12] [W] [TRT] Tactic Device request: 4377MB Available: 1680MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:12] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4377 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:12] [W] [TRT] Tactic Device request: 2185MB Available: 1680MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:12] [W] [TRT] Skipping tactic 16 due to insufficient memory on requested size of 2185 detected for tactic 0x0000000000000075.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:17] [W] [TRT] Tactic Device request: 4375MB Available: 1680MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:17] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4375 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:18] [W] [TRT] Tactic Device request: 2183MB Available: 1680MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:18] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2183 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:18] [W] [TRT] Tactic Device request: 4375MB Available: 1680MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:18] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4375 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:18] [W] [TRT] Tactic Device request: 2183MB Available: 1680MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:18] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2183 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:22] [W] [TRT] Tactic Device request: 4376MB Available: 1680MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:22] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4376 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:22] [W] [TRT] Tactic Device request: 2184MB Available: 1680MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:22] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2184 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:22] [W] [TRT] Tactic Device request: 4376MB Available: 1679MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:22] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4376 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:22] [W] [TRT] Tactic Device request: 2184MB Available: 1679MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:22] [W] [TRT] Skipping tactic 10 due to insufficient memory on requested size of 2184 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:23] [W] [TRT] Tactic Device request: 4376MB Available: 1679MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:23] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4376 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:23] [W] [TRT] Tactic Device request: 2184MB Available: 1679MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:23] [W] [TRT] Skipping tactic 16 due to insufficient memory on requested size of 2184 detected for tactic 0x0000000000000075.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:28] [W] [TRT] Tactic Device request: 4375MB Available: 1679MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:28] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4375 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:28] [W] [TRT] Tactic Device request: 2183MB Available: 1679MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:28] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2183 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:29] [W] [TRT] Tactic Device request: 4375MB Available: 1679MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:29] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4375 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:57:29] [W] [TRT] Tactic Device request: 2183MB Available: 1679MB. Device memory is insufficient to use tactic.
+[12/28/2023-12:57:29] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2183 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-12:58:16] [W] [TRT] TensorRT encountered issues when converting weights between types and that could affect accuracy.
+[12/28/2023-12:58:16] [W] [TRT] If this is not the desired behavior, please modify the weights or retrain with regularization to adjust the magnitude of the weights.
+[12/28/2023-12:58:16] [W] [TRT] Check verbose logs for the list of affected weights.
+[12/28/2023-12:58:16] [W] [TRT] - 114 weights are affected by this issue: Detected subnormal FP16 values.
+[12/28/2023-12:58:16] [W] [TRT] - 40 weights are affected by this issue: Detected values less than smallest positive FP16 subnormal value and converted them to the FP16 minimum subnormalized value.
+[12/28/2023-12:58:33] [W] * Throughput may be bound by Enqueue Time rather than GPU Compute and the GPU may be under-utilized.
+[12/28/2023-12:58:33] [W]   If not already in use, --useCudaGraph (utilize CUDA graphs where possible) may increase the throughput.
+[12/28/2023-12:58:33] [W] * GPU compute time is unstable, with coefficient of variance = 5.80641%.
+[12/28/2023-12:58:33] [W]   If not already in use, locking GPU clock frequency or adding --useSpinWait may improve the stability.

yolo_nas_pose_l_fp32.onnx.fp16.engine.log

@@ -0,0 +1,328 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp32.onnx --fp16 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp32.onnx.fp16.engine
+[12/28/2023-11:52:55] [I] === Model Options ===
+[12/28/2023-11:52:55] [I] Format: ONNX
+[12/28/2023-11:52:55] [I] Model: yolo_nas_pose_l_fp32.onnx
+[12/28/2023-11:52:55] [I] Output:
+[12/28/2023-11:52:55] [I] === Build Options ===
+[12/28/2023-11:52:55] [I] Max batch: explicit batch
+[12/28/2023-11:52:55] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-11:52:55] [I] minTiming: 1
+[12/28/2023-11:52:55] [I] avgTiming: 8
+[12/28/2023-11:52:55] [I] Precision: FP32+FP16
+[12/28/2023-11:52:55] [I] LayerPrecisions: 
+[12/28/2023-11:52:55] [I] Calibration: 
+[12/28/2023-11:52:55] [I] Refit: Disabled
+[12/28/2023-11:52:55] [I] Sparsity: Disabled
+[12/28/2023-11:52:55] [I] Safe mode: Disabled
+[12/28/2023-11:52:55] [I] DirectIO mode: Disabled
+[12/28/2023-11:52:55] [I] Restricted mode: Disabled
+[12/28/2023-11:52:55] [I] Build only: Disabled
+[12/28/2023-11:52:55] [I] Save engine: yolo_nas_pose_l_fp32.onnx.fp16.engine
+[12/28/2023-11:52:55] [I] Load engine: 
+[12/28/2023-11:52:55] [I] Profiling verbosity: 0
+[12/28/2023-11:52:55] [I] Tactic sources: Using default tactic sources
+[12/28/2023-11:52:55] [I] timingCacheMode: local
+[12/28/2023-11:52:55] [I] timingCacheFile: 
+[12/28/2023-11:52:55] [I] Heuristic: Disabled
+[12/28/2023-11:52:55] [I] Preview Features: Use default preview flags.
+[12/28/2023-11:52:55] [I] Input(s)s format: fp32:CHW
+[12/28/2023-11:52:55] [I] Output(s)s format: fp32:CHW
+[12/28/2023-11:52:55] [I] Input build shapes: model
+[12/28/2023-11:52:55] [I] Input calibration shapes: model
+[12/28/2023-11:52:55] [I] === System Options ===
+[12/28/2023-11:52:55] [I] Device: 0
+[12/28/2023-11:52:55] [I] DLACore: 
+[12/28/2023-11:52:55] [I] Plugins:
+[12/28/2023-11:52:55] [I] === Inference Options ===
+[12/28/2023-11:52:55] [I] Batch: Explicit
+[12/28/2023-11:52:55] [I] Input inference shapes: model
+[12/28/2023-11:52:55] [I] Iterations: 10
+[12/28/2023-11:52:55] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-11:52:55] [I] Sleep time: 0ms
+[12/28/2023-11:52:55] [I] Idle time: 0ms
+[12/28/2023-11:52:55] [I] Streams: 1
+[12/28/2023-11:52:55] [I] ExposeDMA: Disabled
+[12/28/2023-11:52:55] [I] Data transfers: Enabled
+[12/28/2023-11:52:55] [I] Spin-wait: Disabled
+[12/28/2023-11:52:55] [I] Multithreading: Disabled
+[12/28/2023-11:52:55] [I] CUDA Graph: Disabled
+[12/28/2023-11:52:55] [I] Separate profiling: Disabled
+[12/28/2023-11:52:55] [I] Time Deserialize: Disabled
+[12/28/2023-11:52:55] [I] Time Refit: Disabled
+[12/28/2023-11:52:55] [I] NVTX verbosity: 0
+[12/28/2023-11:52:55] [I] Persistent Cache Ratio: 0
+[12/28/2023-11:52:55] [I] Inputs:
+[12/28/2023-11:52:55] [I] === Reporting Options ===
+[12/28/2023-11:52:55] [I] Verbose: Disabled
+[12/28/2023-11:52:55] [I] Averages: 100 inferences
+[12/28/2023-11:52:55] [I] Percentiles: 90,95,99
+[12/28/2023-11:52:55] [I] Dump refittable layers:Disabled
+[12/28/2023-11:52:55] [I] Dump output: Disabled
+[12/28/2023-11:52:55] [I] Profile: Disabled
+[12/28/2023-11:52:55] [I] Export timing to JSON file: 
+[12/28/2023-11:52:55] [I] Export output to JSON file: 
+[12/28/2023-11:52:55] [I] Export profile to JSON file: 
+[12/28/2023-11:52:55] [I] 
+[12/28/2023-11:52:55] [I] === Device Information ===
+[12/28/2023-11:52:55] [I] Selected Device: Orin
+[12/28/2023-11:52:55] [I] Compute Capability: 8.7
+[12/28/2023-11:52:55] [I] SMs: 8
+[12/28/2023-11:52:55] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-11:52:55] [I] Device Global Memory: 7471 MiB
+[12/28/2023-11:52:55] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-11:52:55] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-11:52:55] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-11:52:55] [I] 
+[12/28/2023-11:52:55] [I] TensorRT version: 8.5.2
+[12/28/2023-11:52:56] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 3001 (MiB)
+[12/28/2023-11:52:59] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +283, now: CPU 574, GPU 3306 (MiB)
+[12/28/2023-11:52:59] [I] Start parsing network model
+[12/28/2023-11:53:02] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-11:53:02] [I] [TRT] Input filename:   yolo_nas_pose_l_fp32.onnx
+[12/28/2023-11:53:02] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-11:53:02] [I] [TRT] Opset version:    17
+[12/28/2023-11:53:02] [I] [TRT] Producer name:    pytorch
+[12/28/2023-11:53:02] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-11:53:02] [I] [TRT] Domain:           
+[12/28/2023-11:53:02] [I] [TRT] Model version:    0
+[12/28/2023-11:53:02] [I] [TRT] Doc string:       
+[12/28/2023-11:53:02] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-11:53:03] [I] Finish parsing network model
+[12/28/2023-11:53:04] [I] [TRT] ---------- Layers Running on DLA ----------
+[12/28/2023-11:53:04] [I] [TRT] ---------- Layers Running on GPU ----------
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation1]
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/pre_process/pre_process.0/Cast.../pre_process/pre_process.2/Mul]}
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 455) [Constant]
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 456) [Constant]
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 457) [Constant]
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stem/conv/rbr_reparam/Conv + /model/backbone/stem/conv/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/downsample/rbr_reparam/Conv + /model/backbone/stage1/downsample/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv2/conv/Conv + /model/backbone/stage1/blocks/conv2/act/Relu || /model/backbone/stage1/blocks/conv1/conv/Conv + /model/backbone/stage1/blocks/conv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 15) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 23) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv3/conv/Conv + /model/backbone/stage1/blocks/conv3/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_skip2/conv/Conv + /model/neck/neck2/reduce_skip2/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/downsample/rbr_reparam/Conv + /model/backbone/stage2/downsample/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/downsample/conv/Conv + /model/neck/neck2/downsample/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv2/conv/Conv + /model/backbone/stage2/blocks/conv2/act/Relu || /model/backbone/stage2/blocks/conv1/conv/Conv + /model/backbone/stage2/blocks/conv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 44) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 52) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 60) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv3/conv/Conv + /model/backbone/stage2/blocks/conv3/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip2/conv/Conv + /model/neck/neck1/reduce_skip2/act/Relu || /model/neck/neck2/reduce_skip1/conv/Conv + /model/neck/neck2/reduce_skip1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/downsample/rbr_reparam/Conv + /model/backbone/stage3/downsample/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/downsample/conv/Conv + /model/neck/neck1/downsample/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv2/conv/Conv + /model/backbone/stage3/blocks/conv2/act/Relu || /model/backbone/stage3/blocks/conv1/conv/Conv + /model/backbone/stage3/blocks/conv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 83) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 91) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 99) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 107) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.4.alpha + (Unnamed Layer* 115) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv3/conv/Conv + /model/backbone/stage3/blocks/conv3/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip1/conv/Conv + /model/neck/neck1/reduce_skip1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/downsample/rbr_reparam/Conv + /model/backbone/stage4/downsample/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv2/conv/Conv + /model/backbone/stage4/blocks/conv2/act/Relu || /model/backbone/stage4/blocks/conv1/conv/Conv + /model/backbone/stage4/blocks/conv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 134) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 142) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv3/conv/Conv + /model/backbone/stage4/blocks/conv3/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv1/conv/Conv + /model/backbone/context_module/cv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.2/MaxPool
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.1/MaxPool
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.0/MaxPool
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/backbone/context_module/cv1/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv2/conv/Conv + /model/backbone/context_module/cv2/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/conv/conv/Conv + /model/neck/neck1/conv/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck1/upsample/ConvTranspose
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_after_concat/conv/Conv + /model/neck/neck1/reduce_after_concat/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv2/conv/Conv + /model/neck/neck1/blocks/conv2/act/Relu || /model/neck/neck1/blocks/conv1/conv/Conv + /model/neck/neck1/blocks/conv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 171) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 179) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.2.alpha + (Unnamed Layer* 187) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.3.alpha + (Unnamed Layer* 195) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv3/conv/Conv + /model/neck/neck1/blocks/conv3/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/conv/conv/Conv + /model/neck/neck2/conv/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck2/upsample/ConvTranspose
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/reduce_skip1/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_after_concat/conv/Conv + /model/neck/neck2/reduce_after_concat/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv2/conv/Conv + /model/neck/neck2/blocks/conv2/act/Relu || /model/neck/neck2/blocks/conv1/conv/Conv + /model/neck/neck2/blocks/conv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 216) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 224) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 232) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.3.alpha + (Unnamed Layer* 240) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv3/conv/Conv + /model/neck/neck2/blocks/conv3/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/bbox_stem/seq/conv/Conv + /model/heads/head1/bbox_stem/seq/act/Relu || /model/heads/head1/pose_stem/seq/conv/Conv + /model/heads/head1/pose_stem/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/conv/conv/Conv + /model/neck/neck3/conv/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head1/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head1/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head1/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv2/conv/Conv + /model/neck/neck3/blocks/conv2/act/Relu || /model/neck/neck3/blocks/conv1/conv/Conv + /model/neck/neck3/blocks/conv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/cls_pred/Conv
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_pred/Conv
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape + /model/heads/Transpose
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_pred/Conv
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 271) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 294) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 302) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 310) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv3/conv/Conv + /model/neck/neck3/blocks/conv3/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_stem/seq/conv/Conv + /model/heads/head2/pose_stem/seq/act/Relu || /model/heads/head2/bbox_stem/seq/conv/Conv + /model/heads/head2/bbox_stem/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/conv/conv/Conv + /model/neck/neck4/conv/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head2/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head2/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head2/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv2/conv/Conv + /model/neck/neck4/blocks/conv2/act/Relu || /model/neck/neck4/blocks/conv1/conv/Conv + /model/neck/neck4/blocks/conv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/cls_pred/Conv
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_pred/Conv
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_4 + /model/heads/Transpose_3
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_pred/Conv
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_1
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 341) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_1
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 364) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.2.alpha + (Unnamed Layer* 372) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.3.alpha + (Unnamed Layer* 380) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv3/conv/Conv + /model/neck/neck4/blocks/conv3/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/bbox_stem/seq/conv/Conv + /model/heads/head3/bbox_stem/seq/act/Relu || /model/heads/head3/pose_stem/seq/conv/Conv + /model/heads/head3/pose_stem/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head3/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head3/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head3/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/cls_pred/Conv
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_pred/Conv
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_8 + /model/heads/Transpose_6
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.2/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.2/seq/act/Relu
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_2
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_pred/Conv
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_2
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice_1.../post_process/Reshape_2]}
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] NMS: batched_nms_26
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] DEVICE_TO_SHAPE_HOST: (Unnamed Layer* 459) [NMS]_1_output[DevicetoShapeHostCopy]
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation2]
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice...graph2_/Concat_5]}
+[12/28/2023-11:53:04] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation3]
+[12/28/2023-11:53:10] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +534, GPU +444, now: CPU 1350, GPU 4042 (MiB)
+[12/28/2023-11:53:11] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +83, GPU +74, now: CPU 1433, GPU 4116 (MiB)
+[12/28/2023-11:53:11] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
+[12/28/2023-12:57:56] [I] [TRT] Total Activation Memory: 8060146176
+[12/28/2023-12:57:56] [I] [TRT] Detected 1 inputs and 1 output network tensors.
+[12/28/2023-12:58:10] [I] [TRT] Total Host Persistent Memory: 376864
+[12/28/2023-12:58:10] [I] [TRT] Total Device Persistent Memory: 61440
+[12/28/2023-12:58:10] [I] [TRT] Total Scratch Memory: 134217728
+[12/28/2023-12:58:10] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 139 MiB, GPU 2131 MiB
+[12/28/2023-12:58:10] [I] [TRT] [BlockAssignment] Started assigning block shifts. This will take 209 steps to complete.
+[12/28/2023-12:58:10] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 267.621ms to assign 16 blocks to 209 nodes requiring 160521216 bytes.
+[12/28/2023-12:58:10] [I] [TRT] Total Activation Memory: 160521216
+[12/28/2023-12:58:16] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +0, now: CPU 1885, GPU 5668 (MiB)
+[12/28/2023-12:58:16] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +104, GPU +128, now: CPU 104, GPU 128 (MiB)
+[12/28/2023-12:58:17] [I] Engine built in 3922.11 sec.
+[12/28/2023-12:58:17] [I] [TRT] Loaded engine size: 105 MiB
+[12/28/2023-12:58:18] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1347, GPU 5215 (MiB)
+[12/28/2023-12:58:18] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +103, now: CPU 0, GPU 103 (MiB)
+[12/28/2023-12:58:18] [I] Engine deserialized in 0.277587 sec.
+[12/28/2023-12:58:18] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1348, GPU 5215 (MiB)
+[12/28/2023-12:58:18] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +154, now: CPU 0, GPU 257 (MiB)
+[12/28/2023-12:58:18] [I] Setting persistentCacheLimit to 0 bytes.
+[12/28/2023-12:58:18] [I] Using random values for input onnx::Cast_0
+[12/28/2023-12:58:18] [I] Created input binding for onnx::Cast_0 with dimensions 1x3x640x640
+[12/28/2023-12:58:18] [I] Using random values for output graph2_flat_predictions
+[12/28/2023-12:58:18] [I] Created output binding for graph2_flat_predictions with dimensions -1x57
+[12/28/2023-12:58:18] [I] Starting inference
+[12/28/2023-12:58:33] [I] Warmup completed 2 queries over 200 ms
+[12/28/2023-12:58:33] [I] Timing trace has 437 queries over 15.0687 s
+[12/28/2023-12:58:33] [I] 
+[12/28/2023-12:58:33] [I] === Trace details ===
+[12/28/2023-12:58:33] [I] Trace averages of 100 runs:
+[12/28/2023-12:58:33] [I] Average on 100 runs - GPU latency: 34.2122 ms - Host latency: 34.3209 ms (enqueue 34.261 ms)
+[12/28/2023-12:58:33] [I] Average on 100 runs - GPU latency: 34.6286 ms - Host latency: 34.7419 ms (enqueue 34.6733 ms)
+[12/28/2023-12:58:33] [I] Average on 100 runs - GPU latency: 34.32 ms - Host latency: 34.4264 ms (enqueue 34.3737 ms)
+[12/28/2023-12:58:33] [I] Average on 100 runs - GPU latency: 34.1213 ms - Host latency: 34.2258 ms (enqueue 34.1666 ms)
+[12/28/2023-12:58:33] [I] 
+[12/28/2023-12:58:33] [I] === Performance summary ===
+[12/28/2023-12:58:33] [I] Throughput: 29.0005 qps
+[12/28/2023-12:58:33] [I] Latency: min = 32.0405 ms, max = 46.5195 ms, mean = 34.4576 ms, median = 34.021 ms, percentile(90%) = 35.2378 ms, percentile(95%) = 37.8905 ms, percentile(99%) = 44.1553 ms
+[12/28/2023-12:58:33] [I] Enqueue Time: min = 32.0081 ms, max = 46.4473 ms, mean = 34.3937 ms, median = 33.9883 ms, percentile(90%) = 35.166 ms, percentile(95%) = 37.6458 ms, percentile(99%) = 44.0703 ms
+[12/28/2023-12:58:33] [I] H2D Latency: min = 0.0800781 ms, max = 0.119629 ms, mean = 0.0890405 ms, median = 0.0893555 ms, percentile(90%) = 0.0913086 ms, percentile(95%) = 0.0917969 ms, percentile(99%) = 0.103516 ms
+[12/28/2023-12:58:33] [I] GPU Compute Time: min = 31.9365 ms, max = 46.3989 ms, mean = 34.3493 ms, median = 33.9121 ms, percentile(90%) = 35.1299 ms, percentile(95%) = 37.7999 ms, percentile(99%) = 44.0645 ms
+[12/28/2023-12:58:33] [I] D2H Latency: min = 0.00292969 ms, max = 0.0566406 ms, mean = 0.0192997 ms, median = 0.0175781 ms, percentile(90%) = 0.0292969 ms, percentile(95%) = 0.03125 ms, percentile(99%) = 0.0371094 ms
+[12/28/2023-12:58:33] [I] Total Host Walltime: 15.0687 s
+[12/28/2023-12:58:33] [I] Total GPU Compute Time: 15.0106 s
+[12/28/2023-12:58:33] [I] Explanations of the performance metrics are printed in the verbose logs.
+[12/28/2023-12:58:33] [I] 
+&&&& PASSED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp32.onnx --fp16 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp32.onnx.fp16.engine

yolo_nas_pose_l_fp32.onnx.int8.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48058cfe18fb0bfcfbf2822e4ac65f9801a49f738a3d6718eff46f2237aeee33
+size 57073047

yolo_nas_pose_l_fp32.onnx.int8.engine.err

@@ -0,0 +1,256 @@
+[12/28/2023-15:10:20] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-15:10:20] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-15:10:21] [W] [TRT] Calibrator is not being used. Users must provide dynamic range for all tensors that are not Int32 or Bool.
+[12/28/2023-15:17:13] [W] [TRT] Tactic Device request: 4720MB Available: 2708MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:17:13] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4720 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:17:14] [W] [TRT] Tactic Device request: 4720MB Available: 2708MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:17:14] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4720 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:17:14] [W] [TRT] Tactic Device request: 4720MB Available: 2707MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:17:14] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4720 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:17:21] [W] [TRT] Tactic Device request: 4711MB Available: 2698MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:17:21] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:17:22] [W] [TRT] Tactic Device request: 4711MB Available: 2697MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:17:22] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:17:22] [W] [TRT] Tactic Device request: 4711MB Available: 2702MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:17:22] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:17:29] [W] [TRT] Tactic Device request: 4711MB Available: 2688MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:17:29] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:17:30] [W] [TRT] Tactic Device request: 4711MB Available: 2689MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:17:30] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:17:30] [W] [TRT] Tactic Device request: 4711MB Available: 2689MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:17:30] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:21:24] [W] [TRT] Tactic Device request: 4711MB Available: 2366MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:21:24] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:21:24] [W] [TRT] Tactic Device request: 4711MB Available: 2366MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:21:24] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:21:24] [W] [TRT] Tactic Device request: 4711MB Available: 2366MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:21:24] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:21:39] [W] [TRT] Tactic Device request: 6275MB Available: 2366MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:21:39] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:21:39] [W] [TRT] Tactic Device request: 6275MB Available: 2366MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:21:39] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6275 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:21:39] [W] [TRT] Tactic Device request: 6275MB Available: 2366MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:21:39] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:27:20] [W] [TRT] Tactic Device request: 7056MB Available: 2259MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:27:20] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:27:20] [W] [TRT] Tactic Device request: 7056MB Available: 2257MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:27:20] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 7056 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:27:20] [W] [TRT] Tactic Device request: 7056MB Available: 2257MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:27:20] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:27:36] [W] [TRT] Tactic Device request: 6354MB Available: 2258MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:27:36] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:27:36] [W] [TRT] Tactic Device request: 6354MB Available: 2258MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:27:36] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6354 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:27:36] [W] [TRT] Tactic Device request: 6354MB Available: 2258MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:27:36] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:28] [W] [TRT] Tactic Device request: 2394MB Available: 2120MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:28] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2394 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:28] [W] [TRT] Tactic Device request: 2394MB Available: 2120MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:28] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2394 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:28] [W] [TRT] Tactic Device request: 2394MB Available: 2120MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:28] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2394 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:29] [W] [TRT] Tactic Device request: 2392MB Available: 2120MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:29] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:29] [W] [TRT] Tactic Device request: 2392MB Available: 2120MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:29] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2392 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:29] [W] [TRT] Tactic Device request: 2392MB Available: 2120MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:29] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:42] [W] [TRT] Tactic Device request: 6540MB Available: 2103MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:42] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6540 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:42] [W] [TRT] Tactic Device request: 6540MB Available: 2103MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:42] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6540 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:42] [W] [TRT] Tactic Device request: 6540MB Available: 2103MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:42] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6540 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:46] [W] [TRT] Tactic Device request: 2191MB Available: 2103MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:46] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2191 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:47] [W] [TRT] Tactic Device request: 2191MB Available: 2102MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:47] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2191 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:48] [W] [TRT] Tactic Device request: 2191MB Available: 2100MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:48] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2191 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:53] [W] [TRT] Tactic Device request: 2190MB Available: 2102MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:53] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:54] [W] [TRT] Tactic Device request: 2190MB Available: 2099MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:54] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:35:55] [W] [TRT] Tactic Device request: 2190MB Available: 2100MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:35:55] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:36:01] [W] [TRT] Tactic Device request: 2190MB Available: 2100MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:36:01] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:36:02] [W] [TRT] Tactic Device request: 2190MB Available: 2100MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:36:02] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2190 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:36:03] [W] [TRT] Tactic Device request: 2190MB Available: 2099MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:36:03] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2190 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:40:03] [W] [TRT] Tactic Device request: 2457MB Available: 2339MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:40:03] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2457 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:40:03] [W] [TRT] Tactic Device request: 2457MB Available: 2339MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:40:03] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:40:23] [W] [TRT] Tactic Device request: 3587MB Available: 2337MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:40:23] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:40:23] [W] [TRT] Tactic Device request: 3587MB Available: 2337MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:40:23] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3587 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:40:23] [W] [TRT] Tactic Device request: 3587MB Available: 2337MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:40:23] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:47:03] [W] [TRT] Tactic Device request: 3556MB Available: 2223MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:47:03] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:47:03] [W] [TRT] Tactic Device request: 3556MB Available: 2223MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:47:03] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3556 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:47:03] [W] [TRT] Tactic Device request: 3556MB Available: 2223MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:47:03] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:47:05] [W] [TRT] Tactic Device request: 3140MB Available: 2192MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:47:05] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3140 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:47:05] [W] [TRT] Tactic Device request: 3140MB Available: 2191MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:47:05] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3140 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:47:06] [W] [TRT] Tactic Device request: 3140MB Available: 2191MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:47:06] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3140 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:53:21] [W] [TRT] Tactic Device request: 3161MB Available: 2119MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:53:21] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3161 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:53:21] [W] [TRT] Tactic Device request: 3161MB Available: 2119MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:53:21] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3161 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:53:21] [W] [TRT] Tactic Device request: 3161MB Available: 2119MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:53:21] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3161 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:53:26] [W] [TRT] Tactic Device request: 4189MB Available: 2117MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:53:26] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4189 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:53:27] [W] [TRT] Tactic Device request: 4189MB Available: 2101MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:53:27] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4189 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:53:27] [W] [TRT] Tactic Device request: 4189MB Available: 2101MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:53:27] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4189 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:53:33] [W] [TRT] Tactic Device request: 4186MB Available: 2099MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:53:33] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4186 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:53:33] [W] [TRT] Tactic Device request: 4186MB Available: 2099MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:53:33] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4186 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-15:53:33] [W] [TRT] Tactic Device request: 4186MB Available: 2099MB. Device memory is insufficient to use tactic.
+[12/28/2023-15:53:34] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4186 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:00:19] [W] [TRT] Tactic Device request: 4764MB Available: 2172MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:00:19] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4764 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:00:19] [W] [TRT] Tactic Device request: 4764MB Available: 2170MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:00:19] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4764 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:00:19] [W] [TRT] Tactic Device request: 4764MB Available: 2170MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:00:19] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4764 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:00:26] [W] [TRT] Tactic Device request: 4244MB Available: 2030MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:00:26] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4244 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:00:27] [W] [TRT] Tactic Device request: 4244MB Available: 1979MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:00:27] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4244 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:00:28] [W] [TRT] Tactic Device request: 4244MB Available: 1979MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:00:28] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4244 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:00:35] [W] [TRT] Tactic Device request: 4241MB Available: 1980MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:00:35] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4241 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:00:36] [W] [TRT] Tactic Device request: 4241MB Available: 1980MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:00:36] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4241 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:00:37] [W] [TRT] Tactic Device request: 4241MB Available: 1979MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:00:37] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4241 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:17] [W] [TRT] Tactic Device request: 3270MB Available: 1808MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:17] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3270 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:17] [W] [TRT] Tactic Device request: 3270MB Available: 1808MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:17] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3270 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:17] [W] [TRT] Tactic Device request: 3270MB Available: 1808MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:17] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3270 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:21] [W] [TRT] Tactic Device request: 4377MB Available: 1804MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:21] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4377 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:21] [W] [TRT] Tactic Device request: 2185MB Available: 1804MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:21] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2185 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:21] [W] [TRT] Tactic Device request: 4377MB Available: 1804MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:21] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4377 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:21] [W] [TRT] Tactic Device request: 2185MB Available: 1804MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:21] [W] [TRT] Skipping tactic 10 due to insufficient memory on requested size of 2185 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:22] [W] [TRT] Tactic Device request: 4377MB Available: 1803MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:22] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4377 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:22] [W] [TRT] Tactic Device request: 2185MB Available: 1803MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:22] [W] [TRT] Skipping tactic 16 due to insufficient memory on requested size of 2185 detected for tactic 0x0000000000000075.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:31] [W] [TRT] Tactic Device request: 4376MB Available: 1803MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:31] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4376 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:31] [W] [TRT] Tactic Device request: 2184MB Available: 1803MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:31] [W] [TRT] Skipping tactic 4 due to insufficient memory on requested size of 2184 detected for tactic 0x0000000000000005.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:31] [W] [TRT] Tactic Device request: 4376MB Available: 1803MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:31] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4376 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:31] [W] [TRT] Tactic Device request: 2184MB Available: 1803MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:31] [W] [TRT] Skipping tactic 10 due to insufficient memory on requested size of 2184 detected for tactic 0x000000000000003d.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:32] [W] [TRT] Tactic Device request: 4376MB Available: 1803MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:32] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4376 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:08:32] [W] [TRT] Tactic Device request: 2184MB Available: 1803MB. Device memory is insufficient to use tactic.
+[12/28/2023-16:08:32] [W] [TRT] Skipping tactic 16 due to insufficient memory on requested size of 2184 detected for tactic 0x0000000000000075.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-16:09:30] [W] * Throughput may be bound by Enqueue Time rather than GPU Compute and the GPU may be under-utilized.
+[12/28/2023-16:09:30] [W]   If not already in use, --useCudaGraph (utilize CUDA graphs where possible) may increase the throughput.
+[12/28/2023-16:09:30] [W] * GPU compute time is unstable, with coefficient of variance = 6.6527%.
+[12/28/2023-16:09:30] [W]   If not already in use, locking GPU clock frequency or adding --useSpinWait may improve the stability.

yolo_nas_pose_l_fp32.onnx.int8.engine.log

@@ -0,0 +1,332 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp32.onnx --int8 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp32.onnx.int8.engine
+[12/28/2023-15:10:07] [I] === Model Options ===
+[12/28/2023-15:10:07] [I] Format: ONNX
+[12/28/2023-15:10:07] [I] Model: yolo_nas_pose_l_fp32.onnx
+[12/28/2023-15:10:07] [I] Output:
+[12/28/2023-15:10:07] [I] === Build Options ===
+[12/28/2023-15:10:07] [I] Max batch: explicit batch
+[12/28/2023-15:10:07] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-15:10:07] [I] minTiming: 1
+[12/28/2023-15:10:07] [I] avgTiming: 8
+[12/28/2023-15:10:07] [I] Precision: FP32+INT8
+[12/28/2023-15:10:07] [I] LayerPrecisions: 
+[12/28/2023-15:10:07] [I] Calibration: Dynamic
+[12/28/2023-15:10:07] [I] Refit: Disabled
+[12/28/2023-15:10:07] [I] Sparsity: Disabled
+[12/28/2023-15:10:07] [I] Safe mode: Disabled
+[12/28/2023-15:10:07] [I] DirectIO mode: Disabled
+[12/28/2023-15:10:07] [I] Restricted mode: Disabled
+[12/28/2023-15:10:07] [I] Build only: Disabled
+[12/28/2023-15:10:07] [I] Save engine: yolo_nas_pose_l_fp32.onnx.int8.engine
+[12/28/2023-15:10:07] [I] Load engine: 
+[12/28/2023-15:10:07] [I] Profiling verbosity: 0
+[12/28/2023-15:10:07] [I] Tactic sources: Using default tactic sources
+[12/28/2023-15:10:07] [I] timingCacheMode: local
+[12/28/2023-15:10:07] [I] timingCacheFile: 
+[12/28/2023-15:10:07] [I] Heuristic: Disabled
+[12/28/2023-15:10:07] [I] Preview Features: Use default preview flags.
+[12/28/2023-15:10:07] [I] Input(s)s format: fp32:CHW
+[12/28/2023-15:10:07] [I] Output(s)s format: fp32:CHW
+[12/28/2023-15:10:07] [I] Input build shapes: model
+[12/28/2023-15:10:07] [I] Input calibration shapes: model
+[12/28/2023-15:10:07] [I] === System Options ===
+[12/28/2023-15:10:07] [I] Device: 0
+[12/28/2023-15:10:07] [I] DLACore: 
+[12/28/2023-15:10:07] [I] Plugins:
+[12/28/2023-15:10:07] [I] === Inference Options ===
+[12/28/2023-15:10:07] [I] Batch: Explicit
+[12/28/2023-15:10:07] [I] Input inference shapes: model
+[12/28/2023-15:10:07] [I] Iterations: 10
+[12/28/2023-15:10:07] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-15:10:07] [I] Sleep time: 0ms
+[12/28/2023-15:10:07] [I] Idle time: 0ms
+[12/28/2023-15:10:07] [I] Streams: 1
+[12/28/2023-15:10:07] [I] ExposeDMA: Disabled
+[12/28/2023-15:10:07] [I] Data transfers: Enabled
+[12/28/2023-15:10:07] [I] Spin-wait: Disabled
+[12/28/2023-15:10:07] [I] Multithreading: Disabled
+[12/28/2023-15:10:07] [I] CUDA Graph: Disabled
+[12/28/2023-15:10:07] [I] Separate profiling: Disabled
+[12/28/2023-15:10:07] [I] Time Deserialize: Disabled
+[12/28/2023-15:10:07] [I] Time Refit: Disabled
+[12/28/2023-15:10:07] [I] NVTX verbosity: 0
+[12/28/2023-15:10:07] [I] Persistent Cache Ratio: 0
+[12/28/2023-15:10:07] [I] Inputs:
+[12/28/2023-15:10:07] [I] === Reporting Options ===
+[12/28/2023-15:10:07] [I] Verbose: Disabled
+[12/28/2023-15:10:07] [I] Averages: 100 inferences
+[12/28/2023-15:10:07] [I] Percentiles: 90,95,99
+[12/28/2023-15:10:07] [I] Dump refittable layers:Disabled
+[12/28/2023-15:10:07] [I] Dump output: Disabled
+[12/28/2023-15:10:07] [I] Profile: Disabled
+[12/28/2023-15:10:07] [I] Export timing to JSON file: 
+[12/28/2023-15:10:07] [I] Export output to JSON file: 
+[12/28/2023-15:10:07] [I] Export profile to JSON file: 
+[12/28/2023-15:10:07] [I] 
+[12/28/2023-15:10:07] [I] === Device Information ===
+[12/28/2023-15:10:07] [I] Selected Device: Orin
+[12/28/2023-15:10:07] [I] Compute Capability: 8.7
+[12/28/2023-15:10:07] [I] SMs: 8
+[12/28/2023-15:10:07] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-15:10:07] [I] Device Global Memory: 7471 MiB
+[12/28/2023-15:10:07] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-15:10:07] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-15:10:07] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-15:10:07] [I] 
+[12/28/2023-15:10:07] [I] TensorRT version: 8.5.2
+[12/28/2023-15:10:12] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 3019 (MiB)
+[12/28/2023-15:10:17] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +286, now: CPU 574, GPU 3326 (MiB)
+[12/28/2023-15:10:17] [I] Start parsing network model
+[12/28/2023-15:10:20] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-15:10:20] [I] [TRT] Input filename:   yolo_nas_pose_l_fp32.onnx
+[12/28/2023-15:10:20] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-15:10:20] [I] [TRT] Opset version:    17
+[12/28/2023-15:10:20] [I] [TRT] Producer name:    pytorch
+[12/28/2023-15:10:20] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-15:10:20] [I] [TRT] Domain:           
+[12/28/2023-15:10:20] [I] [TRT] Model version:    0
+[12/28/2023-15:10:20] [I] [TRT] Doc string:       
+[12/28/2023-15:10:20] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-15:10:21] [I] Finish parsing network model
+[12/28/2023-15:10:21] [I] FP32 and INT8 precisions have been specified - more performance might be enabled by additionally specifying --fp16 or --best
+[12/28/2023-15:10:21] [I] [TRT] ---------- Layers Running on DLA ----------
+[12/28/2023-15:10:21] [I] [TRT] ---------- Layers Running on GPU ----------
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation1]
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/pre_process/pre_process.0/Cast.../pre_process/pre_process.2/Mul]}
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 455) [Constant]
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 456) [Constant]
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 457) [Constant]
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stem/conv/rbr_reparam/Conv + /model/backbone/stem/conv/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/downsample/rbr_reparam/Conv + /model/backbone/stage1/downsample/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv2/conv/Conv + /model/backbone/stage1/blocks/conv2/act/Relu || /model/backbone/stage1/blocks/conv1/conv/Conv + /model/backbone/stage1/blocks/conv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 15) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 23) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv3/conv/Conv + /model/backbone/stage1/blocks/conv3/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_skip2/conv/Conv + /model/neck/neck2/reduce_skip2/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/downsample/rbr_reparam/Conv + /model/backbone/stage2/downsample/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/downsample/conv/Conv + /model/neck/neck2/downsample/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv2/conv/Conv + /model/backbone/stage2/blocks/conv2/act/Relu || /model/backbone/stage2/blocks/conv1/conv/Conv + /model/backbone/stage2/blocks/conv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 44) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 52) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 60) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv3/conv/Conv + /model/backbone/stage2/blocks/conv3/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip2/conv/Conv + /model/neck/neck1/reduce_skip2/act/Relu || /model/neck/neck2/reduce_skip1/conv/Conv + /model/neck/neck2/reduce_skip1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/downsample/rbr_reparam/Conv + /model/backbone/stage3/downsample/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/downsample/conv/Conv + /model/neck/neck1/downsample/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv2/conv/Conv + /model/backbone/stage3/blocks/conv2/act/Relu || /model/backbone/stage3/blocks/conv1/conv/Conv + /model/backbone/stage3/blocks/conv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 83) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 91) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 99) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 107) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.4.alpha + (Unnamed Layer* 115) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv3/conv/Conv + /model/backbone/stage3/blocks/conv3/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip1/conv/Conv + /model/neck/neck1/reduce_skip1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/downsample/rbr_reparam/Conv + /model/backbone/stage4/downsample/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv2/conv/Conv + /model/backbone/stage4/blocks/conv2/act/Relu || /model/backbone/stage4/blocks/conv1/conv/Conv + /model/backbone/stage4/blocks/conv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 134) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 142) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv3/conv/Conv + /model/backbone/stage4/blocks/conv3/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv1/conv/Conv + /model/backbone/context_module/cv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.2/MaxPool
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.1/MaxPool
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.0/MaxPool
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/backbone/context_module/cv1/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv2/conv/Conv + /model/backbone/context_module/cv2/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/conv/conv/Conv + /model/neck/neck1/conv/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck1/upsample/ConvTranspose
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_after_concat/conv/Conv + /model/neck/neck1/reduce_after_concat/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv2/conv/Conv + /model/neck/neck1/blocks/conv2/act/Relu || /model/neck/neck1/blocks/conv1/conv/Conv + /model/neck/neck1/blocks/conv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 171) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 179) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.2.alpha + (Unnamed Layer* 187) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.3.alpha + (Unnamed Layer* 195) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv3/conv/Conv + /model/neck/neck1/blocks/conv3/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/conv/conv/Conv + /model/neck/neck2/conv/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck2/upsample/ConvTranspose
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/reduce_skip1/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_after_concat/conv/Conv + /model/neck/neck2/reduce_after_concat/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv2/conv/Conv + /model/neck/neck2/blocks/conv2/act/Relu || /model/neck/neck2/blocks/conv1/conv/Conv + /model/neck/neck2/blocks/conv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 216) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 224) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 232) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.3.alpha + (Unnamed Layer* 240) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv3/conv/Conv + /model/neck/neck2/blocks/conv3/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/bbox_stem/seq/conv/Conv + /model/heads/head1/bbox_stem/seq/act/Relu || /model/heads/head1/pose_stem/seq/conv/Conv + /model/heads/head1/pose_stem/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/conv/conv/Conv + /model/neck/neck3/conv/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head1/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head1/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head1/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv2/conv/Conv + /model/neck/neck3/blocks/conv2/act/Relu || /model/neck/neck3/blocks/conv1/conv/Conv + /model/neck/neck3/blocks/conv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/cls_pred/Conv
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_pred/Conv
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape + /model/heads/Transpose
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_pred/Conv
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 271) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 294) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 302) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 310) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv3/conv/Conv + /model/neck/neck3/blocks/conv3/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_stem/seq/conv/Conv + /model/heads/head2/pose_stem/seq/act/Relu || /model/heads/head2/bbox_stem/seq/conv/Conv + /model/heads/head2/bbox_stem/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/conv/conv/Conv + /model/neck/neck4/conv/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head2/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head2/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head2/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv2/conv/Conv + /model/neck/neck4/blocks/conv2/act/Relu || /model/neck/neck4/blocks/conv1/conv/Conv + /model/neck/neck4/blocks/conv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/cls_pred/Conv
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_pred/Conv
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_4 + /model/heads/Transpose_3
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_pred/Conv
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_1
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 341) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_1
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 364) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.2.alpha + (Unnamed Layer* 372) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.3.alpha + (Unnamed Layer* 380) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv3/conv/Conv + /model/neck/neck4/blocks/conv3/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/bbox_stem/seq/conv/Conv + /model/heads/head3/bbox_stem/seq/act/Relu || /model/heads/head3/pose_stem/seq/conv/Conv + /model/heads/head3/pose_stem/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head3/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head3/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head3/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/cls_pred/Conv
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_pred/Conv
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_8 + /model/heads/Transpose_6
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.2/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.2/seq/act/Relu
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_2
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_pred/Conv
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_2
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice_1.../post_process/Reshape_2]}
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] NMS: batched_nms_26
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] DEVICE_TO_SHAPE_HOST: (Unnamed Layer* 459) [NMS]_1_output[DevicetoShapeHostCopy]
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation2]
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice...graph2_/Concat_5]}
+[12/28/2023-15:10:21] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation3]
+[12/28/2023-15:10:35] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +534, GPU +335, now: CPU 1351, GPU 3954 (MiB)
+[12/28/2023-15:10:37] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +82, GPU +63, now: CPU 1433, GPU 4017 (MiB)
+[12/28/2023-15:10:37] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
+[12/28/2023-16:08:54] [I] [TRT] Total Activation Memory: 7959592448
+[12/28/2023-16:08:54] [I] [TRT] Detected 1 inputs and 1 output network tensors.
+[12/28/2023-16:09:08] [I] [TRT] Total Host Persistent Memory: 331808
+[12/28/2023-16:09:08] [I] [TRT] Total Device Persistent Memory: 38912
+[12/28/2023-16:09:08] [I] [TRT] Total Scratch Memory: 134217728
+[12/28/2023-16:09:08] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 88 MiB, GPU 2461 MiB
+[12/28/2023-16:09:08] [I] [TRT] [BlockAssignment] Started assigning block shifts. This will take 160 steps to complete.
+[12/28/2023-16:09:08] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 55.0722ms to assign 13 blocks to 160 nodes requiring 147361280 bytes.
+[12/28/2023-16:09:08] [I] [TRT] Total Activation Memory: 147361280
+[12/28/2023-16:09:13] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU -1, now: CPU 1835, GPU 5360 (MiB)
+[12/28/2023-16:09:13] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +52, GPU +64, now: CPU 52, GPU 64 (MiB)
+[12/28/2023-16:09:14] [I] Engine built in 3546.25 sec.
+[12/28/2023-16:09:14] [I] [TRT] Loaded engine size: 54 MiB
+[12/28/2023-16:09:15] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1299, GPU 5007 (MiB)
+[12/28/2023-16:09:15] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +52, now: CPU 0, GPU 52 (MiB)
+[12/28/2023-16:09:15] [I] Engine deserialized in 0.128069 sec.
+[12/28/2023-16:09:15] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +0, now: CPU 1300, GPU 5007 (MiB)
+[12/28/2023-16:09:15] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +140, now: CPU 0, GPU 192 (MiB)
+[12/28/2023-16:09:15] [I] Setting persistentCacheLimit to 0 bytes.
+[12/28/2023-16:09:15] [I] Using random values for input onnx::Cast_0
+[12/28/2023-16:09:15] [I] Created input binding for onnx::Cast_0 with dimensions 1x3x640x640
+[12/28/2023-16:09:15] [I] Using random values for output graph2_flat_predictions
+[12/28/2023-16:09:15] [I] Created output binding for graph2_flat_predictions with dimensions -1x57
+[12/28/2023-16:09:15] [I] Starting inference
+[12/28/2023-16:09:30] [I] Warmup completed 3 queries over 200 ms
+[12/28/2023-16:09:30] [I] Timing trace has 720 queries over 15.0291 s
+[12/28/2023-16:09:30] [I] 
+[12/28/2023-16:09:30] [I] === Trace details ===
+[12/28/2023-16:09:30] [I] Trace averages of 100 runs:
+[12/28/2023-16:09:30] [I] Average on 100 runs - GPU latency: 20.9331 ms - Host latency: 21.0491 ms (enqueue 20.9849 ms)
+[12/28/2023-16:09:30] [I] Average on 100 runs - GPU latency: 20.3949 ms - Host latency: 20.5041 ms (enqueue 20.4581 ms)
+[12/28/2023-16:09:30] [I] Average on 100 runs - GPU latency: 20.9551 ms - Host latency: 21.0733 ms (enqueue 21.0198 ms)
+[12/28/2023-16:09:30] [I] Average on 100 runs - GPU latency: 20.8394 ms - Host latency: 20.9537 ms (enqueue 20.8945 ms)
+[12/28/2023-16:09:30] [I] Average on 100 runs - GPU latency: 20.4666 ms - Host latency: 20.5773 ms (enqueue 20.5432 ms)
+[12/28/2023-16:09:30] [I] Average on 100 runs - GPU latency: 20.689 ms - Host latency: 20.8023 ms (enqueue 20.7502 ms)
+[12/28/2023-16:09:30] [I] Average on 100 runs - GPU latency: 20.7472 ms - Host latency: 20.8614 ms (enqueue 20.8134 ms)
+[12/28/2023-16:09:30] [I] 
+[12/28/2023-16:09:30] [I] === Performance summary ===
+[12/28/2023-16:09:30] [I] Throughput: 47.9071 qps
+[12/28/2023-16:09:30] [I] Latency: min = 19.4119 ms, max = 30.8398 ms, mean = 20.8421 ms, median = 20.7168 ms, percentile(90%) = 21.5566 ms, percentile(95%) = 22.2598 ms, percentile(99%) = 28.5723 ms
+[12/28/2023-16:09:30] [I] Enqueue Time: min = 19.3838 ms, max = 30.7852 ms, mean = 20.7908 ms, median = 20.6725 ms, percentile(90%) = 21.4995 ms, percentile(95%) = 22.1094 ms, percentile(99%) = 28.5068 ms
+[12/28/2023-16:09:30] [I] H2D Latency: min = 0.0800781 ms, max = 0.133301 ms, mean = 0.0950138 ms, median = 0.0957031 ms, percentile(90%) = 0.0981445 ms, percentile(95%) = 0.0986328 ms, percentile(99%) = 0.0996094 ms
+[12/28/2023-16:09:30] [I] GPU Compute Time: min = 19.304 ms, max = 30.7158 ms, mean = 20.7286 ms, median = 20.5989 ms, percentile(90%) = 21.4419 ms, percentile(95%) = 22.1621 ms, percentile(99%) = 28.4521 ms
+[12/28/2023-16:09:30] [I] D2H Latency: min = 0.00292969 ms, max = 0.0688477 ms, mean = 0.0184459 ms, median = 0.0166016 ms, percentile(90%) = 0.0273438 ms, percentile(95%) = 0.0288086 ms, percentile(99%) = 0.0444336 ms
+[12/28/2023-16:09:30] [I] Total Host Walltime: 15.0291 s
+[12/28/2023-16:09:30] [I] Total GPU Compute Time: 14.9246 s
+[12/28/2023-16:09:30] [I] Explanations of the performance metrics are printed in the verbose logs.
+[12/28/2023-16:09:30] [I] 
+&&&& PASSED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_fp32.onnx --int8 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_fp32.onnx.int8.engine

yolo_nas_pose_l_fp32.onnx.usage.txt

@@ -0,0 +1,58 @@
+
+Model exported successfully to yolo_nas_pose_l_fp32.onnx
+Model expects input image of shape [1, 3, 640, 640]
+Input image dtype is torch.uint8
+
+Exported model already contains preprocessing (normalization) step, so you don't need to do it manually.
+Preprocessing steps to be applied to input image are:
+Sequential(
+  (0): CastTensorTo(dtype=torch.float32)
+  (1): ChannelSelect(channels_indexes=tensor([2, 1, 0]))
+  (2): ApplyMeanStd(mean=[0.], scale=[255.])
+)
+
+
+Exported model contains postprocessing (NMS) step with the following parameters:
+    num_pre_nms_predictions=1000
+    max_predictions_per_image=10
+    nms_threshold=0.5
+    confidence_threshold=0.15
+    output_predictions_format=flat
+
+
+Exported model is in ONNX format and can be used with ONNXRuntime
+To run inference with ONNXRuntime, please use the following code snippet:
+
+    import onnxruntime
+    import numpy as np
+    session = onnxruntime.InferenceSession("yolo_nas_pose_l_fp32.onnx", providers=["CUDAExecutionProvider", "CPUExecutionProvider"])
+    inputs = [o.name for o in session.get_inputs()]
+    outputs = [o.name for o in session.get_outputs()]
+
+    example_input_image = np.zeros((1, 3, 640, 640)).astype(np.uint8)
+    predictions = session.run(outputs, {inputs[0]: example_input_image})
+
+Exported model can also be used with TensorRT
+To run inference with TensorRT, please see TensorRT deployment documentation
+You can benchmark the model using the following code snippet:
+
+    trtexec --onnx=yolo_nas_pose_l_fp32.onnx --fp16 --avgRuns=100 --duration=15
+
+
+Exported model has predictions in flat format:
+
+# flat_predictions is a 2D array of [N,K] shape
+# Each row represents (image_index, x_min, y_min, x_max, y_max, confidence, joints...)
+# Please note all values are floats, so you have to convert them to integers if needed
+
+[flat_predictions] = predictions
+pred_bboxes = flat_predictions[:, 1:5]
+pred_scores = flat_predictions[:, 5]
+pred_joints = flat_predictions[:, 6:].reshape((len(pred_bboxes), -1, 3))
+for i in range(len(pred_bboxes)):
+    confidence = pred_scores[i]
+    x_min, y_min, x_max, y_max = pred_bboxes[i]
+    print(f"Detected pose with confidence={{confidence}}, x_min={{x_min}}, y_min={{y_min}}, x_max={{x_max}}, y_max={{y_max}}")
+    for joint_index, (x, y, confidence) in enumerate(pred_joints[i]):")
+        print(f"Joint {{joint_index}} has coordinates x={{x}}, y={{y}}, confidence={{confidence}}")
+

yolo_nas_pose_l_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3acfcfd2f63c649f1a6695ff7c3a77dbfb67f654592ddf1abb8f5d32c2efd0cb
+size 218735221

yolo_nas_pose_l_int8.onnx.best.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6be26b88c524b32a7fe99eeaa6166ae80bd428e90d7f45b24317115286e1c80
+size 57269617

yolo_nas_pose_l_int8.onnx.best.engine.err

@@ -0,0 +1,7 @@
+[12/28/2023-19:27:37] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-19:27:37] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-19:27:42] [W] [TRT] Calibrator won't be used in explicit precision mode. Use quantization aware training to generate network with Quantize/Dequantize nodes.
+[12/28/2023-20:16:25] [W] * Throughput may be bound by Enqueue Time rather than GPU Compute and the GPU may be under-utilized.
+[12/28/2023-20:16:25] [W]   If not already in use, --useCudaGraph (utilize CUDA graphs where possible) may increase the throughput.
+[12/28/2023-20:16:25] [W] * GPU compute time is unstable, with coefficient of variance = 6.69708%.
+[12/28/2023-20:16:25] [W]   If not already in use, locking GPU clock frequency or adding --useSpinWait may improve the stability.

yolo_nas_pose_l_int8.onnx.best.engine.log

@@ -0,0 +1,357 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_int8.onnx --best --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_int8.onnx.best.engine
+[12/28/2023-19:27:34] [I] === Model Options ===
+[12/28/2023-19:27:34] [I] Format: ONNX
+[12/28/2023-19:27:34] [I] Model: yolo_nas_pose_l_int8.onnx
+[12/28/2023-19:27:34] [I] Output:
+[12/28/2023-19:27:34] [I] === Build Options ===
+[12/28/2023-19:27:34] [I] Max batch: explicit batch
+[12/28/2023-19:27:34] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-19:27:34] [I] minTiming: 1
+[12/28/2023-19:27:34] [I] avgTiming: 8
+[12/28/2023-19:27:34] [I] Precision: FP32+FP16+INT8
+[12/28/2023-19:27:34] [I] LayerPrecisions: 
+[12/28/2023-19:27:34] [I] Calibration: Dynamic
+[12/28/2023-19:27:34] [I] Refit: Disabled
+[12/28/2023-19:27:34] [I] Sparsity: Disabled
+[12/28/2023-19:27:34] [I] Safe mode: Disabled
+[12/28/2023-19:27:34] [I] DirectIO mode: Disabled
+[12/28/2023-19:27:34] [I] Restricted mode: Disabled
+[12/28/2023-19:27:34] [I] Build only: Disabled
+[12/28/2023-19:27:34] [I] Save engine: yolo_nas_pose_l_int8.onnx.best.engine
+[12/28/2023-19:27:34] [I] Load engine: 
+[12/28/2023-19:27:34] [I] Profiling verbosity: 0
+[12/28/2023-19:27:34] [I] Tactic sources: Using default tactic sources
+[12/28/2023-19:27:34] [I] timingCacheMode: local
+[12/28/2023-19:27:34] [I] timingCacheFile: 
+[12/28/2023-19:27:34] [I] Heuristic: Disabled
+[12/28/2023-19:27:34] [I] Preview Features: Use default preview flags.
+[12/28/2023-19:27:34] [I] Input(s)s format: fp32:CHW
+[12/28/2023-19:27:34] [I] Output(s)s format: fp32:CHW
+[12/28/2023-19:27:34] [I] Input build shapes: model
+[12/28/2023-19:27:34] [I] Input calibration shapes: model
+[12/28/2023-19:27:34] [I] === System Options ===
+[12/28/2023-19:27:34] [I] Device: 0
+[12/28/2023-19:27:34] [I] DLACore: 
+[12/28/2023-19:27:34] [I] Plugins:
+[12/28/2023-19:27:34] [I] === Inference Options ===
+[12/28/2023-19:27:34] [I] Batch: Explicit
+[12/28/2023-19:27:34] [I] Input inference shapes: model
+[12/28/2023-19:27:34] [I] Iterations: 10
+[12/28/2023-19:27:34] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-19:27:34] [I] Sleep time: 0ms
+[12/28/2023-19:27:34] [I] Idle time: 0ms
+[12/28/2023-19:27:34] [I] Streams: 1
+[12/28/2023-19:27:34] [I] ExposeDMA: Disabled
+[12/28/2023-19:27:34] [I] Data transfers: Enabled
+[12/28/2023-19:27:34] [I] Spin-wait: Disabled
+[12/28/2023-19:27:34] [I] Multithreading: Disabled
+[12/28/2023-19:27:34] [I] CUDA Graph: Disabled
+[12/28/2023-19:27:34] [I] Separate profiling: Disabled
+[12/28/2023-19:27:34] [I] Time Deserialize: Disabled
+[12/28/2023-19:27:34] [I] Time Refit: Disabled
+[12/28/2023-19:27:34] [I] NVTX verbosity: 0
+[12/28/2023-19:27:34] [I] Persistent Cache Ratio: 0
+[12/28/2023-19:27:34] [I] Inputs:
+[12/28/2023-19:27:34] [I] === Reporting Options ===
+[12/28/2023-19:27:34] [I] Verbose: Disabled
+[12/28/2023-19:27:34] [I] Averages: 100 inferences
+[12/28/2023-19:27:34] [I] Percentiles: 90,95,99
+[12/28/2023-19:27:34] [I] Dump refittable layers:Disabled
+[12/28/2023-19:27:34] [I] Dump output: Disabled
+[12/28/2023-19:27:34] [I] Profile: Disabled
+[12/28/2023-19:27:34] [I] Export timing to JSON file: 
+[12/28/2023-19:27:34] [I] Export output to JSON file: 
+[12/28/2023-19:27:34] [I] Export profile to JSON file: 
+[12/28/2023-19:27:34] [I] 
+[12/28/2023-19:27:34] [I] === Device Information ===
+[12/28/2023-19:27:34] [I] Selected Device: Orin
+[12/28/2023-19:27:34] [I] Compute Capability: 8.7
+[12/28/2023-19:27:34] [I] SMs: 8
+[12/28/2023-19:27:34] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-19:27:34] [I] Device Global Memory: 7471 MiB
+[12/28/2023-19:27:34] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-19:27:34] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-19:27:34] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-19:27:34] [I] 
+[12/28/2023-19:27:34] [I] TensorRT version: 8.5.2
+[12/28/2023-19:27:35] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 2833 (MiB)
+[12/28/2023-19:27:37] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +284, now: CPU 574, GPU 3138 (MiB)
+[12/28/2023-19:27:37] [I] Start parsing network model
+[12/28/2023-19:27:37] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-19:27:37] [I] [TRT] Input filename:   yolo_nas_pose_l_int8.onnx
+[12/28/2023-19:27:37] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-19:27:37] [I] [TRT] Opset version:    17
+[12/28/2023-19:27:37] [I] [TRT] Producer name:    pytorch
+[12/28/2023-19:27:37] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-19:27:37] [I] [TRT] Domain:           
+[12/28/2023-19:27:37] [I] [TRT] Model version:    0
+[12/28/2023-19:27:37] [I] [TRT] Doc string:       
+[12/28/2023-19:27:37] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-19:27:42] [I] Finish parsing network model
+[12/28/2023-19:27:47] [I] [TRT] ---------- Layers Running on DLA ----------
+[12/28/2023-19:27:47] [I] [TRT] ---------- Layers Running on GPU ----------
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation1]
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/pre_process/pre_process.0/Cast.../pre_process/pre_process.2/Mul]}
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 1417) [Constant]
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 1418) [Constant]
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 1419) [Constant]
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stem/conv/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stem.conv.rbr_reparam.weight + /model/backbone/stem/conv/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stem/conv/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.downsample.rbr_reparam.weight + /model/backbone/stage1/downsample/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/downsample/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.conv2.conv.weight + /model/backbone/stage1/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/conv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.conv1.conv.weight + /model/backbone/stage1/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/conv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.bottlenecks.0.cv1.rbr_reparam.weight + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.bottlenecks.0.cv2.rbr_reparam.weight + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 557) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.bottlenecks.1.cv1.rbr_reparam.weight + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.bottlenecks.1.cv2.rbr_reparam.weight + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 573) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_1
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_0
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.conv3.conv.weight + /model/backbone/stage1/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/conv3/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.reduce_skip2.conv.weight + /model/neck/neck2/reduce_skip2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/reduce_skip2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.downsample.rbr_reparam.weight + /model/backbone/stage2/downsample/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/downsample/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.downsample.conv.weight + /model/neck/neck2/downsample/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/downsample/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.conv2.conv.weight + /model/backbone/stage2/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/conv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.conv1.conv.weight + /model/backbone/stage2/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/conv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.bottlenecks.0.cv1.rbr_reparam.weight + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.bottlenecks.0.cv2.rbr_reparam.weight + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 620) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.bottlenecks.1.cv1.rbr_reparam.weight + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.bottlenecks.1.cv2.rbr_reparam.weight + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 636) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.bottlenecks.2.cv1.rbr_reparam.weight + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.bottlenecks.2.cv2.rbr_reparam.weight + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 652) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_2
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_1
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_0
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.conv3.conv.weight + /model/backbone/stage2/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/conv3/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.reduce_skip2.conv.weight + /model/neck/neck1/reduce_skip2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/reduce_skip2/conv/Conv || model.neck.neck2.reduce_skip1.conv.weight + /model/neck/neck2/reduce_skip1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/reduce_skip1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.downsample.rbr_reparam.weight + /model/backbone/stage3/downsample/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/downsample/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.downsample.conv.weight + /model/neck/neck1/downsample/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/downsample/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.conv2.conv.weight + /model/backbone/stage3/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/conv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.conv1.conv.weight + /model/backbone/stage3/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/conv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.0.cv1.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.0.cv2.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 702) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.1.cv1.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.1.cv2.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 718) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.2.cv1.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.2.cv2.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 734) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.3.cv1.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.3.cv2.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 750) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.4.cv1.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.4.cv2.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.4.alpha + (Unnamed Layer* 766) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_4
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_2
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_1
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_0
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.conv3.conv.weight + /model/backbone/stage3/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/conv3/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.reduce_skip1.conv.weight + /model/neck/neck1/reduce_skip1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/reduce_skip1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.downsample.rbr_reparam.weight + /model/backbone/stage4/downsample/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/downsample/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.conv2.conv.weight + /model/backbone/stage4/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/conv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.conv1.conv.weight + /model/backbone/stage4/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/conv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.bottlenecks.0.cv1.rbr_reparam.weight + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.bottlenecks.0.cv2.rbr_reparam.weight + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 806) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.bottlenecks.1.cv1.rbr_reparam.weight + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.bottlenecks.1.cv2.rbr_reparam.weight + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 822) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_1
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_0
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.conv3.conv.weight + /model/backbone/stage4/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/conv3/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.context_module.cv1.conv.weight + /model/backbone/context_module/cv1/conv/_weight_quantizer/QuantizeLinear + /model/backbone/context_module/cv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.2/MaxPool
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.1/MaxPool
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.0/MaxPool
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/backbone/context_module/m.2/MaxPool_output_0 copy
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.context_module.cv2.conv.weight + /model/backbone/context_module/cv2/conv/_weight_quantizer/QuantizeLinear + /model/backbone/context_module/cv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.conv.conv.weight + /model/neck/neck1/conv/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/conv/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] DECONVOLUTION: model.neck.neck1.upsample.weight + /model/neck/neck1/upsample/_weight_quantizer/QuantizeLinear + /model/neck/neck1/upsample/ConvTranspose
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.reduce_after_concat.conv.weight + /model/neck/neck1/reduce_after_concat/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/reduce_after_concat/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.conv2.conv.weight + /model/neck/neck1/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/conv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.conv1.conv.weight + /model/neck/neck1/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/conv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.0.cv1.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.0.cv2.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 887) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.1.cv1.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.1.cv2.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 903) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.2.cv1.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.2.cv2.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.2.alpha + (Unnamed Layer* 919) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.3.cv1.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.3.cv2.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.3.alpha + (Unnamed Layer* 935) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.conv3.conv.weight + /model/neck/neck1/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/conv3/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.conv.conv.weight + /model/neck/neck2/conv/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/conv/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] DECONVOLUTION: model.neck.neck2.upsample.weight + /model/neck/neck2/upsample/_weight_quantizer/QuantizeLinear + /model/neck/neck2/upsample/ConvTranspose
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/Concat_/model/neck/neck2/reduce_skip1/act/Relu_output_0_clone_1 copy
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.reduce_after_concat.conv.weight + /model/neck/neck2/reduce_after_concat/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/reduce_after_concat/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.conv2.conv.weight + /model/neck/neck2/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/conv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.conv1.conv.weight + /model/neck/neck2/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/conv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.0.cv1.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.0.cv2.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 984) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.1.cv1.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.1.cv2.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 1000) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.2.cv1.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.2.cv2.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 1016) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.3.cv1.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.3.cv2.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.3.alpha + (Unnamed Layer* 1032) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.conv3.conv.weight + /model/neck/neck2/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/conv3/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.bbox_stem.seq.conv.weight + /model/heads/head1/bbox_stem/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head1/bbox_stem/seq/conv/Conv || model.heads.head1.pose_stem.seq.conv.weight + /model/heads/head1/pose_stem/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head1/pose_stem/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.conv.conv.weight + /model/neck/neck3/conv/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/conv/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.reg_convs.0.seq.conv.weight + /model/heads/head1/reg_convs/reg_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head1/reg_convs/reg_convs.0/seq/conv/Conv || model.heads.head1.cls_convs.0.seq.conv.weight + /model/heads/head1/cls_convs/cls_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head1/cls_convs/cls_convs.0/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.pose_convs.0.seq.conv.weight + /model/heads/head1/pose_convs/pose_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head1/pose_convs/pose_convs.0/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.conv2.conv.weight + /model/neck/neck3/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/conv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.conv1.conv.weight + /model/neck/neck3/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/conv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.cls_pred.weight + /model/heads/head1/cls_pred/_weight_quantizer/QuantizeLinear + /model/heads/head1/cls_pred/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.reg_pred.weight + /model/heads/head1/reg_pred/_weight_quantizer/QuantizeLinear + /model/heads/head1/reg_pred/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.pose_convs.1.seq.conv.weight + /model/heads/head1/pose_convs/pose_convs.1/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head1/pose_convs/pose_convs.1/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape + /model/heads/Transpose
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.pose_pred.weight + /model/heads/head1/pose_pred/_weight_quantizer/QuantizeLinear + /model/heads/head1/pose_pred/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.0.cv1.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.0.cv2.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 1097) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.1.cv1.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.1.cv2.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 1138) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.2.cv1.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.2.cv2.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 1154) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.3.cv1.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.3.cv2.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 1170) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.conv3.conv.weight + /model/neck/neck3/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/conv3/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.pose_stem.seq.conv.weight + /model/heads/head2/pose_stem/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head2/pose_stem/seq/conv/Conv || model.heads.head2.bbox_stem.seq.conv.weight + /model/heads/head2/bbox_stem/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head2/bbox_stem/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.conv.conv.weight + /model/neck/neck4/conv/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/conv/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.reg_convs.0.seq.conv.weight + /model/heads/head2/reg_convs/reg_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head2/reg_convs/reg_convs.0/seq/conv/Conv || model.heads.head2.cls_convs.0.seq.conv.weight + /model/heads/head2/cls_convs/cls_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head2/cls_convs/cls_convs.0/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.pose_convs.0.seq.conv.weight + /model/heads/head2/pose_convs/pose_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head2/pose_convs/pose_convs.0/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.conv2.conv.weight + /model/neck/neck4/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/conv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.conv1.conv.weight + /model/neck/neck4/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/conv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.cls_pred.weight + /model/heads/head2/cls_pred/_weight_quantizer/QuantizeLinear + /model/heads/head2/cls_pred/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.reg_pred.weight + /model/heads/head2/reg_pred/_weight_quantizer/QuantizeLinear + /model/heads/head2/reg_pred/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.pose_convs.1.seq.conv.weight + /model/heads/head2/pose_convs/pose_convs.1/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head2/pose_convs/pose_convs.1/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_4 + /model/heads/Transpose_3
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.pose_pred.weight + /model/heads/head2/pose_pred/_weight_quantizer/QuantizeLinear + /model/heads/head2/pose_pred/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.0.cv1.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_1
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.0.cv2.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_1
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 1235) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.1.cv1.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.1.cv2.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 1276) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.2.cv1.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.2.cv2.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.2.alpha + (Unnamed Layer* 1292) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.3.cv1.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.3.cv2.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.3.alpha + (Unnamed Layer* 1308) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.conv3.conv.weight + /model/neck/neck4/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/conv3/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.bbox_stem.seq.conv.weight + /model/heads/head3/bbox_stem/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/bbox_stem/seq/conv/Conv || model.heads.head3.pose_stem.seq.conv.weight + /model/heads/head3/pose_stem/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/pose_stem/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.reg_convs.0.seq.conv.weight + /model/heads/head3/reg_convs/reg_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/reg_convs/reg_convs.0/seq/conv/Conv || model.heads.head3.cls_convs.0.seq.conv.weight + /model/heads/head3/cls_convs/cls_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/cls_convs/cls_convs.0/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.pose_convs.0.seq.conv.weight + /model/heads/head3/pose_convs/pose_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/pose_convs/pose_convs.0/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.cls_pred.weight + /model/heads/head3/cls_pred/_weight_quantizer/QuantizeLinear + /model/heads/head3/cls_pred/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.reg_pred.weight + /model/heads/head3/reg_pred/_weight_quantizer/QuantizeLinear + /model/heads/head3/reg_pred/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.pose_convs.1.seq.conv.weight + /model/heads/head3/pose_convs/pose_convs.1/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/pose_convs/pose_convs.1/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_8 + /model/heads/Transpose_6
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.pose_convs.2.seq.conv.weight + /model/heads/head3/pose_convs/pose_convs.2/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/pose_convs/pose_convs.2/seq/conv/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_2
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.pose_pred.weight + /model/heads/head3/pose_pred/_weight_quantizer/QuantizeLinear + /model/heads/head3/pose_pred/Conv
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_2
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice_1.../post_process/Reshape_2]}
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] NMS: batched_nms_274
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] DEVICE_TO_SHAPE_HOST: (Unnamed Layer* 1421) [NMS]_1_output[DevicetoShapeHostCopy]
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation2]
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice...graph2_/Concat_5]}
+[12/28/2023-19:27:47] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation3]
+[12/28/2023-19:28:00] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +534, GPU +418, now: CPU 1532, GPU 3937 (MiB)
+[12/28/2023-19:28:02] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +83, GPU +79, now: CPU 1615, GPU 4016 (MiB)
+[12/28/2023-19:28:02] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
+[12/28/2023-20:15:51] [I] [TRT] Total Activation Memory: 7994521088
+[12/28/2023-20:15:51] [I] [TRT] Detected 1 inputs and 1 output network tensors.
+[12/28/2023-20:16:04] [I] [TRT] Total Host Persistent Memory: 355104
+[12/28/2023-20:16:04] [I] [TRT] Total Device Persistent Memory: 38912
+[12/28/2023-20:16:04] [I] [TRT] Total Scratch Memory: 134217728
+[12/28/2023-20:16:04] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 264 MiB, GPU 454 MiB
+[12/28/2023-20:16:04] [I] [TRT] [BlockAssignment] Started assigning block shifts. This will take 188 steps to complete.
+[12/28/2023-20:16:04] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 61.0389ms to assign 14 blocks to 188 nodes requiring 156376576 bytes.
+[12/28/2023-20:16:04] [I] [TRT] Total Activation Memory: 156376576
+[12/28/2023-20:16:09] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 2003, GPU 5524 (MiB)
+[12/28/2023-20:16:09] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +52, GPU +64, now: CPU 52, GPU 64 (MiB)
+[12/28/2023-20:16:09] [I] Engine built in 2915.03 sec.
+[12/28/2023-20:16:09] [I] [TRT] Loaded engine size: 54 MiB
+[12/28/2023-20:16:10] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1288, GPU 5322 (MiB)
+[12/28/2023-20:16:10] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +52, now: CPU 0, GPU 52 (MiB)
+[12/28/2023-20:16:10] [I] Engine deserialized in 0.222476 sec.
+[12/28/2023-20:16:10] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1289, GPU 5322 (MiB)
+[12/28/2023-20:16:10] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +149, now: CPU 0, GPU 201 (MiB)
+[12/28/2023-20:16:10] [I] Setting persistentCacheLimit to 0 bytes.
+[12/28/2023-20:16:10] [I] Using random values for input onnx::Cast_0
+[12/28/2023-20:16:10] [I] Created input binding for onnx::Cast_0 with dimensions 1x3x640x640
+[12/28/2023-20:16:10] [I] Using random values for output graph2_flat_predictions
+[12/28/2023-20:16:10] [I] Created output binding for graph2_flat_predictions with dimensions -1x57
+[12/28/2023-20:16:10] [I] Starting inference
+[12/28/2023-20:16:25] [I] Warmup completed 7 queries over 200 ms
+[12/28/2023-20:16:25] [I] Timing trace has 556 queries over 15.0394 s
+[12/28/2023-20:16:25] [I] 
+[12/28/2023-20:16:25] [I] === Trace details ===
+[12/28/2023-20:16:25] [I] Trace averages of 100 runs:
+[12/28/2023-20:16:25] [I] Average on 100 runs - GPU latency: 27.1478 ms - Host latency: 27.2648 ms (enqueue 27.2126 ms)
+[12/28/2023-20:16:25] [I] Average on 100 runs - GPU latency: 26.6955 ms - Host latency: 26.8082 ms (enqueue 26.7744 ms)
+[12/28/2023-20:16:25] [I] Average on 100 runs - GPU latency: 27.0859 ms - Host latency: 27.1971 ms (enqueue 27.1502 ms)
+[12/28/2023-20:16:25] [I] Average on 100 runs - GPU latency: 26.5486 ms - Host latency: 26.6622 ms (enqueue 26.6226 ms)
+[12/28/2023-20:16:25] [I] Average on 100 runs - GPU latency: 26.938 ms - Host latency: 27.049 ms (enqueue 27.01 ms)
+[12/28/2023-20:16:25] [I] 
+[12/28/2023-20:16:25] [I] === Performance summary ===
+[12/28/2023-20:16:25] [I] Throughput: 36.9695 qps
+[12/28/2023-20:16:25] [I] Latency: min = 24.9229 ms, max = 40.8822 ms, mean = 27.0196 ms, median = 26.4901 ms, percentile(90%) = 27.7676 ms, percentile(95%) = 29.9111 ms, percentile(99%) = 36.0352 ms
+[12/28/2023-20:16:25] [I] Enqueue Time: min = 24.9536 ms, max = 40.8246 ms, mean = 26.9763 ms, median = 26.46 ms, percentile(90%) = 27.5393 ms, percentile(95%) = 30.0479 ms, percentile(99%) = 36.1467 ms
+[12/28/2023-20:16:25] [I] H2D Latency: min = 0.0800781 ms, max = 0.117188 ms, mean = 0.0969461 ms, median = 0.0976562 ms, percentile(90%) = 0.100098 ms, percentile(95%) = 0.100586 ms, percentile(99%) = 0.101562 ms
+[12/28/2023-20:16:25] [I] GPU Compute Time: min = 24.8271 ms, max = 40.7577 ms, mean = 26.9066 ms, median = 26.3784 ms, percentile(90%) = 27.6466 ms, percentile(95%) = 29.7852 ms, percentile(99%) = 35.9219 ms
+[12/28/2023-20:16:25] [I] D2H Latency: min = 0.00292969 ms, max = 0.079834 ms, mean = 0.0159901 ms, median = 0.0146484 ms, percentile(90%) = 0.0258789 ms, percentile(95%) = 0.0291748 ms, percentile(99%) = 0.036377 ms
+[12/28/2023-20:16:25] [I] Total Host Walltime: 15.0394 s
+[12/28/2023-20:16:25] [I] Total GPU Compute Time: 14.9601 s
+[12/28/2023-20:16:25] [I] Explanations of the performance metrics are printed in the verbose logs.
+[12/28/2023-20:16:25] [I] 
+&&&& PASSED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_int8.onnx --best --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_int8.onnx.best.engine

yolo_nas_pose_l_int8.onnx.engine.err

@@ -0,0 +1,8 @@
+[12/28/2023-19:27:20] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-19:27:20] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-19:27:24] [E] Error[4]: [network.cpp::validate::2922] Error Code 4: Internal Error (Int8 precision has been set for a layer or layer output, but int8 is not configured in the builder)
+[12/28/2023-19:27:24] [E] Error[2]: [builder.cpp::buildSerializedNetwork::751] Error Code 2: Internal Error (Assertion engine != nullptr failed. )
+[12/28/2023-19:27:24] [E] Engine could not be created from network
+[12/28/2023-19:27:24] [E] Building engine failed
+[12/28/2023-19:27:24] [E] Failed to create engine from model or file.
+[12/28/2023-19:27:24] [E] Engine set up failed

yolo_nas_pose_l_int8.onnx.engine.log

@@ -0,0 +1,91 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_int8.onnx --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_int8.onnx.engine
+[12/28/2023-19:27:14] [I] === Model Options ===
+[12/28/2023-19:27:14] [I] Format: ONNX
+[12/28/2023-19:27:14] [I] Model: yolo_nas_pose_l_int8.onnx
+[12/28/2023-19:27:14] [I] Output:
+[12/28/2023-19:27:14] [I] === Build Options ===
+[12/28/2023-19:27:14] [I] Max batch: explicit batch
+[12/28/2023-19:27:14] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-19:27:14] [I] minTiming: 1
+[12/28/2023-19:27:14] [I] avgTiming: 8
+[12/28/2023-19:27:14] [I] Precision: FP32
+[12/28/2023-19:27:14] [I] LayerPrecisions: 
+[12/28/2023-19:27:14] [I] Calibration: 
+[12/28/2023-19:27:14] [I] Refit: Disabled
+[12/28/2023-19:27:14] [I] Sparsity: Disabled
+[12/28/2023-19:27:14] [I] Safe mode: Disabled
+[12/28/2023-19:27:14] [I] DirectIO mode: Disabled
+[12/28/2023-19:27:14] [I] Restricted mode: Disabled
+[12/28/2023-19:27:14] [I] Build only: Disabled
+[12/28/2023-19:27:14] [I] Save engine: yolo_nas_pose_l_int8.onnx.engine
+[12/28/2023-19:27:14] [I] Load engine: 
+[12/28/2023-19:27:14] [I] Profiling verbosity: 0
+[12/28/2023-19:27:14] [I] Tactic sources: Using default tactic sources
+[12/28/2023-19:27:14] [I] timingCacheMode: local
+[12/28/2023-19:27:14] [I] timingCacheFile: 
+[12/28/2023-19:27:14] [I] Heuristic: Disabled
+[12/28/2023-19:27:14] [I] Preview Features: Use default preview flags.
+[12/28/2023-19:27:14] [I] Input(s)s format: fp32:CHW
+[12/28/2023-19:27:14] [I] Output(s)s format: fp32:CHW
+[12/28/2023-19:27:14] [I] Input build shapes: model
+[12/28/2023-19:27:14] [I] Input calibration shapes: model
+[12/28/2023-19:27:14] [I] === System Options ===
+[12/28/2023-19:27:14] [I] Device: 0
+[12/28/2023-19:27:14] [I] DLACore: 
+[12/28/2023-19:27:14] [I] Plugins:
+[12/28/2023-19:27:14] [I] === Inference Options ===
+[12/28/2023-19:27:14] [I] Batch: Explicit
+[12/28/2023-19:27:14] [I] Input inference shapes: model
+[12/28/2023-19:27:14] [I] Iterations: 10
+[12/28/2023-19:27:14] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-19:27:14] [I] Sleep time: 0ms
+[12/28/2023-19:27:14] [I] Idle time: 0ms
+[12/28/2023-19:27:14] [I] Streams: 1
+[12/28/2023-19:27:14] [I] ExposeDMA: Disabled
+[12/28/2023-19:27:14] [I] Data transfers: Enabled
+[12/28/2023-19:27:14] [I] Spin-wait: Disabled
+[12/28/2023-19:27:14] [I] Multithreading: Disabled
+[12/28/2023-19:27:14] [I] CUDA Graph: Disabled
+[12/28/2023-19:27:14] [I] Separate profiling: Disabled
+[12/28/2023-19:27:14] [I] Time Deserialize: Disabled
+[12/28/2023-19:27:14] [I] Time Refit: Disabled
+[12/28/2023-19:27:14] [I] NVTX verbosity: 0
+[12/28/2023-19:27:14] [I] Persistent Cache Ratio: 0
+[12/28/2023-19:27:14] [I] Inputs:
+[12/28/2023-19:27:14] [I] === Reporting Options ===
+[12/28/2023-19:27:14] [I] Verbose: Disabled
+[12/28/2023-19:27:14] [I] Averages: 100 inferences
+[12/28/2023-19:27:14] [I] Percentiles: 90,95,99
+[12/28/2023-19:27:14] [I] Dump refittable layers:Disabled
+[12/28/2023-19:27:14] [I] Dump output: Disabled
+[12/28/2023-19:27:14] [I] Profile: Disabled
+[12/28/2023-19:27:14] [I] Export timing to JSON file: 
+[12/28/2023-19:27:14] [I] Export output to JSON file: 
+[12/28/2023-19:27:14] [I] Export profile to JSON file: 
+[12/28/2023-19:27:14] [I] 
+[12/28/2023-19:27:14] [I] === Device Information ===
+[12/28/2023-19:27:14] [I] Selected Device: Orin
+[12/28/2023-19:27:14] [I] Compute Capability: 8.7
+[12/28/2023-19:27:14] [I] SMs: 8
+[12/28/2023-19:27:14] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-19:27:14] [I] Device Global Memory: 7471 MiB
+[12/28/2023-19:27:14] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-19:27:14] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-19:27:14] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-19:27:14] [I] 
+[12/28/2023-19:27:14] [I] TensorRT version: 8.5.2
+[12/28/2023-19:27:14] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 2835 (MiB)
+[12/28/2023-19:27:17] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +286, now: CPU 574, GPU 3142 (MiB)
+[12/28/2023-19:27:17] [I] Start parsing network model
+[12/28/2023-19:27:20] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-19:27:20] [I] [TRT] Input filename:   yolo_nas_pose_l_int8.onnx
+[12/28/2023-19:27:20] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-19:27:20] [I] [TRT] Opset version:    17
+[12/28/2023-19:27:20] [I] [TRT] Producer name:    pytorch
+[12/28/2023-19:27:20] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-19:27:20] [I] [TRT] Domain:           
+[12/28/2023-19:27:20] [I] [TRT] Model version:    0
+[12/28/2023-19:27:20] [I] [TRT] Doc string:       
+[12/28/2023-19:27:20] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-19:27:24] [I] Finish parsing network model
+&&&& FAILED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_int8.onnx --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_int8.onnx.engine

yolo_nas_pose_l_int8.onnx.fp16.engine.err

@@ -0,0 +1,8 @@
+[12/28/2023-19:27:29] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-19:27:29] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-19:27:33] [E] Error[4]: [network.cpp::validate::2922] Error Code 4: Internal Error (Int8 precision has been set for a layer or layer output, but int8 is not configured in the builder)
+[12/28/2023-19:27:33] [E] Error[2]: [builder.cpp::buildSerializedNetwork::751] Error Code 2: Internal Error (Assertion engine != nullptr failed. )
+[12/28/2023-19:27:33] [E] Engine could not be created from network
+[12/28/2023-19:27:33] [E] Building engine failed
+[12/28/2023-19:27:33] [E] Failed to create engine from model or file.
+[12/28/2023-19:27:33] [E] Engine set up failed

yolo_nas_pose_l_int8.onnx.fp16.engine.log

@@ -0,0 +1,91 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_int8.onnx --fp16 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_int8.onnx.fp16.engine
+[12/28/2023-19:27:25] [I] === Model Options ===
+[12/28/2023-19:27:25] [I] Format: ONNX
+[12/28/2023-19:27:25] [I] Model: yolo_nas_pose_l_int8.onnx
+[12/28/2023-19:27:25] [I] Output:
+[12/28/2023-19:27:25] [I] === Build Options ===
+[12/28/2023-19:27:25] [I] Max batch: explicit batch
+[12/28/2023-19:27:25] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-19:27:25] [I] minTiming: 1
+[12/28/2023-19:27:25] [I] avgTiming: 8
+[12/28/2023-19:27:25] [I] Precision: FP32+FP16
+[12/28/2023-19:27:25] [I] LayerPrecisions: 
+[12/28/2023-19:27:25] [I] Calibration: 
+[12/28/2023-19:27:25] [I] Refit: Disabled
+[12/28/2023-19:27:25] [I] Sparsity: Disabled
+[12/28/2023-19:27:25] [I] Safe mode: Disabled
+[12/28/2023-19:27:25] [I] DirectIO mode: Disabled
+[12/28/2023-19:27:25] [I] Restricted mode: Disabled
+[12/28/2023-19:27:25] [I] Build only: Disabled
+[12/28/2023-19:27:25] [I] Save engine: yolo_nas_pose_l_int8.onnx.fp16.engine
+[12/28/2023-19:27:25] [I] Load engine: 
+[12/28/2023-19:27:25] [I] Profiling verbosity: 0
+[12/28/2023-19:27:25] [I] Tactic sources: Using default tactic sources
+[12/28/2023-19:27:25] [I] timingCacheMode: local
+[12/28/2023-19:27:25] [I] timingCacheFile: 
+[12/28/2023-19:27:25] [I] Heuristic: Disabled
+[12/28/2023-19:27:25] [I] Preview Features: Use default preview flags.
+[12/28/2023-19:27:25] [I] Input(s)s format: fp32:CHW
+[12/28/2023-19:27:25] [I] Output(s)s format: fp32:CHW
+[12/28/2023-19:27:25] [I] Input build shapes: model
+[12/28/2023-19:27:25] [I] Input calibration shapes: model
+[12/28/2023-19:27:25] [I] === System Options ===
+[12/28/2023-19:27:25] [I] Device: 0
+[12/28/2023-19:27:25] [I] DLACore: 
+[12/28/2023-19:27:25] [I] Plugins:
+[12/28/2023-19:27:25] [I] === Inference Options ===
+[12/28/2023-19:27:25] [I] Batch: Explicit
+[12/28/2023-19:27:25] [I] Input inference shapes: model
+[12/28/2023-19:27:25] [I] Iterations: 10
+[12/28/2023-19:27:25] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-19:27:25] [I] Sleep time: 0ms
+[12/28/2023-19:27:25] [I] Idle time: 0ms
+[12/28/2023-19:27:25] [I] Streams: 1
+[12/28/2023-19:27:25] [I] ExposeDMA: Disabled
+[12/28/2023-19:27:25] [I] Data transfers: Enabled
+[12/28/2023-19:27:25] [I] Spin-wait: Disabled
+[12/28/2023-19:27:25] [I] Multithreading: Disabled
+[12/28/2023-19:27:25] [I] CUDA Graph: Disabled
+[12/28/2023-19:27:25] [I] Separate profiling: Disabled
+[12/28/2023-19:27:25] [I] Time Deserialize: Disabled
+[12/28/2023-19:27:25] [I] Time Refit: Disabled
+[12/28/2023-19:27:25] [I] NVTX verbosity: 0
+[12/28/2023-19:27:25] [I] Persistent Cache Ratio: 0
+[12/28/2023-19:27:25] [I] Inputs:
+[12/28/2023-19:27:25] [I] === Reporting Options ===
+[12/28/2023-19:27:25] [I] Verbose: Disabled
+[12/28/2023-19:27:25] [I] Averages: 100 inferences
+[12/28/2023-19:27:25] [I] Percentiles: 90,95,99
+[12/28/2023-19:27:25] [I] Dump refittable layers:Disabled
+[12/28/2023-19:27:25] [I] Dump output: Disabled
+[12/28/2023-19:27:25] [I] Profile: Disabled
+[12/28/2023-19:27:25] [I] Export timing to JSON file: 
+[12/28/2023-19:27:25] [I] Export output to JSON file: 
+[12/28/2023-19:27:25] [I] Export profile to JSON file: 
+[12/28/2023-19:27:25] [I] 
+[12/28/2023-19:27:25] [I] === Device Information ===
+[12/28/2023-19:27:25] [I] Selected Device: Orin
+[12/28/2023-19:27:25] [I] Compute Capability: 8.7
+[12/28/2023-19:27:25] [I] SMs: 8
+[12/28/2023-19:27:25] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-19:27:25] [I] Device Global Memory: 7471 MiB
+[12/28/2023-19:27:25] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-19:27:25] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-19:27:25] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-19:27:25] [I] 
+[12/28/2023-19:27:25] [I] TensorRT version: 8.5.2
+[12/28/2023-19:27:26] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 2833 (MiB)
+[12/28/2023-19:27:28] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +284, now: CPU 574, GPU 3139 (MiB)
+[12/28/2023-19:27:28] [I] Start parsing network model
+[12/28/2023-19:27:29] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-19:27:29] [I] [TRT] Input filename:   yolo_nas_pose_l_int8.onnx
+[12/28/2023-19:27:29] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-19:27:29] [I] [TRT] Opset version:    17
+[12/28/2023-19:27:29] [I] [TRT] Producer name:    pytorch
+[12/28/2023-19:27:29] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-19:27:29] [I] [TRT] Domain:           
+[12/28/2023-19:27:29] [I] [TRT] Model version:    0
+[12/28/2023-19:27:29] [I] [TRT] Doc string:       
+[12/28/2023-19:27:29] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-19:27:33] [I] Finish parsing network model
+&&&& FAILED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_int8.onnx --fp16 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_int8.onnx.fp16.engine

yolo_nas_pose_l_int8.onnx.int8.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0437c2287a6331143c0b7181c0ce945e117b29eae0d9755f226919acbe4a8cff
+size 57433967

yolo_nas_pose_l_int8.onnx.int8.engine.err

@@ -0,0 +1,7 @@
+[12/28/2023-20:16:35] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-20:16:35] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-20:16:40] [W] [TRT] Calibrator won't be used in explicit precision mode. Use quantization aware training to generate network with Quantize/Dequantize nodes.
+[12/28/2023-20:31:04] [W] * Throughput may be bound by Enqueue Time rather than GPU Compute and the GPU may be under-utilized.
+[12/28/2023-20:31:04] [W]   If not already in use, --useCudaGraph (utilize CUDA graphs where possible) may increase the throughput.
+[12/28/2023-20:31:04] [W] * GPU compute time is unstable, with coefficient of variance = 6.47493%.
+[12/28/2023-20:31:04] [W]   If not already in use, locking GPU clock frequency or adding --useSpinWait may improve the stability.

yolo_nas_pose_l_int8.onnx.int8.engine.log

@@ -0,0 +1,357 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_int8.onnx --int8 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_int8.onnx.int8.engine
+[12/28/2023-20:16:29] [I] === Model Options ===
+[12/28/2023-20:16:29] [I] Format: ONNX
+[12/28/2023-20:16:29] [I] Model: yolo_nas_pose_l_int8.onnx
+[12/28/2023-20:16:29] [I] Output:
+[12/28/2023-20:16:29] [I] === Build Options ===
+[12/28/2023-20:16:29] [I] Max batch: explicit batch
+[12/28/2023-20:16:29] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-20:16:29] [I] minTiming: 1
+[12/28/2023-20:16:29] [I] avgTiming: 8
+[12/28/2023-20:16:29] [I] Precision: FP32+INT8
+[12/28/2023-20:16:29] [I] LayerPrecisions: 
+[12/28/2023-20:16:29] [I] Calibration: Dynamic
+[12/28/2023-20:16:29] [I] Refit: Disabled
+[12/28/2023-20:16:29] [I] Sparsity: Disabled
+[12/28/2023-20:16:29] [I] Safe mode: Disabled
+[12/28/2023-20:16:29] [I] DirectIO mode: Disabled
+[12/28/2023-20:16:29] [I] Restricted mode: Disabled
+[12/28/2023-20:16:29] [I] Build only: Disabled
+[12/28/2023-20:16:29] [I] Save engine: yolo_nas_pose_l_int8.onnx.int8.engine
+[12/28/2023-20:16:29] [I] Load engine: 
+[12/28/2023-20:16:29] [I] Profiling verbosity: 0
+[12/28/2023-20:16:29] [I] Tactic sources: Using default tactic sources
+[12/28/2023-20:16:29] [I] timingCacheMode: local
+[12/28/2023-20:16:29] [I] timingCacheFile: 
+[12/28/2023-20:16:29] [I] Heuristic: Disabled
+[12/28/2023-20:16:29] [I] Preview Features: Use default preview flags.
+[12/28/2023-20:16:29] [I] Input(s)s format: fp32:CHW
+[12/28/2023-20:16:29] [I] Output(s)s format: fp32:CHW
+[12/28/2023-20:16:29] [I] Input build shapes: model
+[12/28/2023-20:16:29] [I] Input calibration shapes: model
+[12/28/2023-20:16:29] [I] === System Options ===
+[12/28/2023-20:16:29] [I] Device: 0
+[12/28/2023-20:16:29] [I] DLACore: 
+[12/28/2023-20:16:29] [I] Plugins:
+[12/28/2023-20:16:29] [I] === Inference Options ===
+[12/28/2023-20:16:29] [I] Batch: Explicit
+[12/28/2023-20:16:29] [I] Input inference shapes: model
+[12/28/2023-20:16:29] [I] Iterations: 10
+[12/28/2023-20:16:29] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-20:16:29] [I] Sleep time: 0ms
+[12/28/2023-20:16:29] [I] Idle time: 0ms
+[12/28/2023-20:16:29] [I] Streams: 1
+[12/28/2023-20:16:29] [I] ExposeDMA: Disabled
+[12/28/2023-20:16:29] [I] Data transfers: Enabled
+[12/28/2023-20:16:29] [I] Spin-wait: Disabled
+[12/28/2023-20:16:29] [I] Multithreading: Disabled
+[12/28/2023-20:16:29] [I] CUDA Graph: Disabled
+[12/28/2023-20:16:29] [I] Separate profiling: Disabled
+[12/28/2023-20:16:29] [I] Time Deserialize: Disabled
+[12/28/2023-20:16:29] [I] Time Refit: Disabled
+[12/28/2023-20:16:29] [I] NVTX verbosity: 0
+[12/28/2023-20:16:29] [I] Persistent Cache Ratio: 0
+[12/28/2023-20:16:29] [I] Inputs:
+[12/28/2023-20:16:29] [I] === Reporting Options ===
+[12/28/2023-20:16:29] [I] Verbose: Disabled
+[12/28/2023-20:16:29] [I] Averages: 100 inferences
+[12/28/2023-20:16:29] [I] Percentiles: 90,95,99
+[12/28/2023-20:16:29] [I] Dump refittable layers:Disabled
+[12/28/2023-20:16:29] [I] Dump output: Disabled
+[12/28/2023-20:16:29] [I] Profile: Disabled
+[12/28/2023-20:16:29] [I] Export timing to JSON file: 
+[12/28/2023-20:16:29] [I] Export output to JSON file: 
+[12/28/2023-20:16:29] [I] Export profile to JSON file: 
+[12/28/2023-20:16:29] [I] 
+[12/28/2023-20:16:29] [I] === Device Information ===
+[12/28/2023-20:16:29] [I] Selected Device: Orin
+[12/28/2023-20:16:29] [I] Compute Capability: 8.7
+[12/28/2023-20:16:29] [I] SMs: 8
+[12/28/2023-20:16:29] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-20:16:29] [I] Device Global Memory: 7471 MiB
+[12/28/2023-20:16:29] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-20:16:29] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-20:16:29] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-20:16:29] [I] 
+[12/28/2023-20:16:29] [I] TensorRT version: 8.5.2
+[12/28/2023-20:16:29] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 2967 (MiB)
+[12/28/2023-20:16:33] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +283, now: CPU 574, GPU 3271 (MiB)
+[12/28/2023-20:16:33] [I] Start parsing network model
+[12/28/2023-20:16:35] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-20:16:35] [I] [TRT] Input filename:   yolo_nas_pose_l_int8.onnx
+[12/28/2023-20:16:35] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-20:16:35] [I] [TRT] Opset version:    17
+[12/28/2023-20:16:35] [I] [TRT] Producer name:    pytorch
+[12/28/2023-20:16:35] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-20:16:35] [I] [TRT] Domain:           
+[12/28/2023-20:16:35] [I] [TRT] Model version:    0
+[12/28/2023-20:16:35] [I] [TRT] Doc string:       
+[12/28/2023-20:16:35] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-20:16:40] [I] Finish parsing network model
+[12/28/2023-20:16:40] [I] FP32 and INT8 precisions have been specified - more performance might be enabled by additionally specifying --fp16 or --best
+[12/28/2023-20:16:45] [I] [TRT] ---------- Layers Running on DLA ----------
+[12/28/2023-20:16:45] [I] [TRT] ---------- Layers Running on GPU ----------
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation1]
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/pre_process/pre_process.0/Cast.../pre_process/pre_process.2/Mul]}
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 1417) [Constant]
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 1418) [Constant]
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 1419) [Constant]
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stem/conv/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stem.conv.rbr_reparam.weight + /model/backbone/stem/conv/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stem/conv/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.downsample.rbr_reparam.weight + /model/backbone/stage1/downsample/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/downsample/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.conv2.conv.weight + /model/backbone/stage1/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/conv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.conv1.conv.weight + /model/backbone/stage1/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/conv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.bottlenecks.0.cv1.rbr_reparam.weight + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.bottlenecks.0.cv2.rbr_reparam.weight + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 557) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.bottlenecks.1.cv1.rbr_reparam.weight + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.bottlenecks.1.cv2.rbr_reparam.weight + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 573) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_1
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_0
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage1.blocks.conv3.conv.weight + /model/backbone/stage1/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage1/blocks/conv3/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.reduce_skip2.conv.weight + /model/neck/neck2/reduce_skip2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/reduce_skip2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.downsample.rbr_reparam.weight + /model/backbone/stage2/downsample/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/downsample/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.downsample.conv.weight + /model/neck/neck2/downsample/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/downsample/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.conv2.conv.weight + /model/backbone/stage2/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/conv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.conv1.conv.weight + /model/backbone/stage2/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/conv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.bottlenecks.0.cv1.rbr_reparam.weight + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.bottlenecks.0.cv2.rbr_reparam.weight + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 620) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.bottlenecks.1.cv1.rbr_reparam.weight + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.bottlenecks.1.cv2.rbr_reparam.weight + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 636) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.bottlenecks.2.cv1.rbr_reparam.weight + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.bottlenecks.2.cv2.rbr_reparam.weight + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 652) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_2
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_1
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_0
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage2.blocks.conv3.conv.weight + /model/backbone/stage2/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage2/blocks/conv3/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.reduce_skip2.conv.weight + /model/neck/neck1/reduce_skip2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/reduce_skip2/conv/Conv || model.neck.neck2.reduce_skip1.conv.weight + /model/neck/neck2/reduce_skip1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/reduce_skip1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.downsample.rbr_reparam.weight + /model/backbone/stage3/downsample/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/downsample/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.downsample.conv.weight + /model/neck/neck1/downsample/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/downsample/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.conv2.conv.weight + /model/backbone/stage3/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/conv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.conv1.conv.weight + /model/backbone/stage3/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/conv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.0.cv1.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.0.cv2.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 702) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.1.cv1.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.1.cv2.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 718) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.2.cv1.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.2.cv2.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 734) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.3.cv1.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.3.cv2.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 750) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.4.cv1.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.bottlenecks.4.cv2.rbr_reparam.weight + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.4.alpha + (Unnamed Layer* 766) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_4
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_2
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_1
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_0
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage3.blocks.conv3.conv.weight + /model/backbone/stage3/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage3/blocks/conv3/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.reduce_skip1.conv.weight + /model/neck/neck1/reduce_skip1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/reduce_skip1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.downsample.rbr_reparam.weight + /model/backbone/stage4/downsample/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/downsample/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.conv2.conv.weight + /model/backbone/stage4/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/conv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.conv1.conv.weight + /model/backbone/stage4/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/conv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.bottlenecks.0.cv1.rbr_reparam.weight + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.bottlenecks.0.cv2.rbr_reparam.weight + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 806) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.bottlenecks.1.cv1.rbr_reparam.weight + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.bottlenecks.1.cv2.rbr_reparam.weight + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 822) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_1
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv3/conv/_input_quantizer/QuantizeLinear_clone_0
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.stage4.blocks.conv3.conv.weight + /model/backbone/stage4/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/backbone/stage4/blocks/conv3/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.context_module.cv1.conv.weight + /model/backbone/context_module/cv1/conv/_weight_quantizer/QuantizeLinear + /model/backbone/context_module/cv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.2/MaxPool
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.1/MaxPool
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.0/MaxPool
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/backbone/context_module/m.2/MaxPool_output_0 copy
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.backbone.context_module.cv2.conv.weight + /model/backbone/context_module/cv2/conv/_weight_quantizer/QuantizeLinear + /model/backbone/context_module/cv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.conv.conv.weight + /model/neck/neck1/conv/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/conv/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] DECONVOLUTION: model.neck.neck1.upsample.weight + /model/neck/neck1/upsample/_weight_quantizer/QuantizeLinear + /model/neck/neck1/upsample/ConvTranspose
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.reduce_after_concat.conv.weight + /model/neck/neck1/reduce_after_concat/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/reduce_after_concat/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.conv2.conv.weight + /model/neck/neck1/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/conv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.conv1.conv.weight + /model/neck/neck1/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/conv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.0.cv1.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.0.cv2.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 887) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.1.cv1.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.1.cv2.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 903) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.2.cv1.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.2.cv2.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.2.alpha + (Unnamed Layer* 919) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.3.cv1.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.bottlenecks.3.cv2.rbr_reparam.weight + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.3.alpha + (Unnamed Layer* 935) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck1.blocks.conv3.conv.weight + /model/neck/neck1/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck1/blocks/conv3/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.conv.conv.weight + /model/neck/neck2/conv/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/conv/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] DECONVOLUTION: model.neck.neck2.upsample.weight + /model/neck/neck2/upsample/_weight_quantizer/QuantizeLinear + /model/neck/neck2/upsample/ConvTranspose
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/Concat_/model/neck/neck2/reduce_skip1/act/Relu_output_0_clone_1 copy
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.reduce_after_concat.conv.weight + /model/neck/neck2/reduce_after_concat/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/reduce_after_concat/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.conv2.conv.weight + /model/neck/neck2/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/conv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.conv1.conv.weight + /model/neck/neck2/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/conv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.0.cv1.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.0.cv2.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 984) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.1.cv1.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.1.cv2.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 1000) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.2.cv1.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.2.cv2.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 1016) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.3.cv1.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.bottlenecks.3.cv2.rbr_reparam.weight + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.3.alpha + (Unnamed Layer* 1032) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck2.blocks.conv3.conv.weight + /model/neck/neck2/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck2/blocks/conv3/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.bbox_stem.seq.conv.weight + /model/heads/head1/bbox_stem/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head1/bbox_stem/seq/conv/Conv || model.heads.head1.pose_stem.seq.conv.weight + /model/heads/head1/pose_stem/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head1/pose_stem/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.conv.conv.weight + /model/neck/neck3/conv/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/conv/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.reg_convs.0.seq.conv.weight + /model/heads/head1/reg_convs/reg_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head1/reg_convs/reg_convs.0/seq/conv/Conv || model.heads.head1.cls_convs.0.seq.conv.weight + /model/heads/head1/cls_convs/cls_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head1/cls_convs/cls_convs.0/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.pose_convs.0.seq.conv.weight + /model/heads/head1/pose_convs/pose_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head1/pose_convs/pose_convs.0/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.conv2.conv.weight + /model/neck/neck3/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/conv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.conv1.conv.weight + /model/neck/neck3/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/conv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.cls_pred.weight + /model/heads/head1/cls_pred/_weight_quantizer/QuantizeLinear + /model/heads/head1/cls_pred/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.reg_pred.weight + /model/heads/head1/reg_pred/_weight_quantizer/QuantizeLinear + /model/heads/head1/reg_pred/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.pose_convs.1.seq.conv.weight + /model/heads/head1/pose_convs/pose_convs.1/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head1/pose_convs/pose_convs.1/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape + /model/heads/Transpose
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head1.pose_pred.weight + /model/heads/head1/pose_pred/_weight_quantizer/QuantizeLinear + /model/heads/head1/pose_pred/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.0.cv1.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.0.cv2.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 1097) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.1.cv1.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.1.cv2.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 1138) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.2.cv1.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.2.cv2.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 1154) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.3.cv1.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.bottlenecks.3.cv2.conv.weight + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 1170) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck3.blocks.conv3.conv.weight + /model/neck/neck3/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck3/blocks/conv3/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.pose_stem.seq.conv.weight + /model/heads/head2/pose_stem/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head2/pose_stem/seq/conv/Conv || model.heads.head2.bbox_stem.seq.conv.weight + /model/heads/head2/bbox_stem/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head2/bbox_stem/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.conv.conv.weight + /model/neck/neck4/conv/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/conv/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.reg_convs.0.seq.conv.weight + /model/heads/head2/reg_convs/reg_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head2/reg_convs/reg_convs.0/seq/conv/Conv || model.heads.head2.cls_convs.0.seq.conv.weight + /model/heads/head2/cls_convs/cls_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head2/cls_convs/cls_convs.0/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.pose_convs.0.seq.conv.weight + /model/heads/head2/pose_convs/pose_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head2/pose_convs/pose_convs.0/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.conv2.conv.weight + /model/neck/neck4/blocks/conv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/conv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.conv1.conv.weight + /model/neck/neck4/blocks/conv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/conv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.cls_pred.weight + /model/heads/head2/cls_pred/_weight_quantizer/QuantizeLinear + /model/heads/head2/cls_pred/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.reg_pred.weight + /model/heads/head2/reg_pred/_weight_quantizer/QuantizeLinear + /model/heads/head2/reg_pred/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.pose_convs.1.seq.conv.weight + /model/heads/head2/pose_convs/pose_convs.1/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head2/pose_convs/pose_convs.1/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_4 + /model/heads/Transpose_3
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head2.pose_pred.weight + /model/heads/head2/pose_pred/_weight_quantizer/QuantizeLinear + /model/heads/head2/pose_pred/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.0.cv1.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_1
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.0.cv2.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_1
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 1235) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.1.cv1.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.1.cv2.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 1276) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.2.cv1.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.2.cv2.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.2.alpha + (Unnamed Layer* 1292) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/conv/_input_quantizer/QuantizeLinear
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.3.cv1.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv1/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.bottlenecks.3.cv2.conv.weight + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/cv2/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.3.alpha + (Unnamed Layer* 1308) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.neck.neck4.blocks.conv3.conv.weight + /model/neck/neck4/blocks/conv3/conv/_weight_quantizer/QuantizeLinear + /model/neck/neck4/blocks/conv3/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.bbox_stem.seq.conv.weight + /model/heads/head3/bbox_stem/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/bbox_stem/seq/conv/Conv || model.heads.head3.pose_stem.seq.conv.weight + /model/heads/head3/pose_stem/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/pose_stem/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.reg_convs.0.seq.conv.weight + /model/heads/head3/reg_convs/reg_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/reg_convs/reg_convs.0/seq/conv/Conv || model.heads.head3.cls_convs.0.seq.conv.weight + /model/heads/head3/cls_convs/cls_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/cls_convs/cls_convs.0/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.pose_convs.0.seq.conv.weight + /model/heads/head3/pose_convs/pose_convs.0/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/pose_convs/pose_convs.0/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.cls_pred.weight + /model/heads/head3/cls_pred/_weight_quantizer/QuantizeLinear + /model/heads/head3/cls_pred/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.reg_pred.weight + /model/heads/head3/reg_pred/_weight_quantizer/QuantizeLinear + /model/heads/head3/reg_pred/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.pose_convs.1.seq.conv.weight + /model/heads/head3/pose_convs/pose_convs.1/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/pose_convs/pose_convs.1/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_8 + /model/heads/Transpose_6
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.pose_convs.2.seq.conv.weight + /model/heads/head3/pose_convs/pose_convs.2/seq/conv/_weight_quantizer/QuantizeLinear + /model/heads/head3/pose_convs/pose_convs.2/seq/conv/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_2
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: model.heads.head3.pose_pred.weight + /model/heads/head3/pose_pred/_weight_quantizer/QuantizeLinear + /model/heads/head3/pose_pred/Conv
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_2
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice_1.../post_process/Reshape_2]}
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] NMS: batched_nms_274
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] DEVICE_TO_SHAPE_HOST: (Unnamed Layer* 1421) [NMS]_1_output[DevicetoShapeHostCopy]
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation2]
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice...graph2_/Concat_5]}
+[12/28/2023-20:16:45] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation3]
+[12/28/2023-20:16:46] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +534, GPU +481, now: CPU 1532, GPU 4180 (MiB)
+[12/28/2023-20:16:47] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +83, GPU +76, now: CPU 1615, GPU 4256 (MiB)
+[12/28/2023-20:16:47] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
+[12/28/2023-20:30:40] [I] [TRT] Total Activation Memory: 8076738048
+[12/28/2023-20:30:40] [I] [TRT] Detected 1 inputs and 1 output network tensors.
+[12/28/2023-20:30:46] [I] [TRT] Total Host Persistent Memory: 355104
+[12/28/2023-20:30:46] [I] [TRT] Total Device Persistent Memory: 38912
+[12/28/2023-20:30:46] [I] [TRT] Total Scratch Memory: 134217728
+[12/28/2023-20:30:46] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 264 MiB, GPU 132 MiB
+[12/28/2023-20:30:46] [I] [TRT] [BlockAssignment] Started assigning block shifts. This will take 194 steps to complete.
+[12/28/2023-20:30:46] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 71.4503ms to assign 13 blocks to 194 nodes requiring 183278080 bytes.
+[12/28/2023-20:30:46] [I] [TRT] Total Activation Memory: 183278080
+[12/28/2023-20:30:48] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +7, now: CPU 2003, GPU 5811 (MiB)
+[12/28/2023-20:30:48] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +52, GPU +64, now: CPU 52, GPU 64 (MiB)
+[12/28/2023-20:30:48] [I] Engine built in 859.207 sec.
+[12/28/2023-20:30:48] [I] [TRT] Loaded engine size: 54 MiB
+[12/28/2023-20:30:48] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +11, now: CPU 1289, GPU 5551 (MiB)
+[12/28/2023-20:30:48] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +52, now: CPU 0, GPU 52 (MiB)
+[12/28/2023-20:30:48] [I] Engine deserialized in 0.183216 sec.
+[12/28/2023-20:30:49] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +6, now: CPU 1289, GPU 5551 (MiB)
+[12/28/2023-20:30:49] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +175, now: CPU 0, GPU 227 (MiB)
+[12/28/2023-20:30:49] [I] Setting persistentCacheLimit to 0 bytes.
+[12/28/2023-20:30:49] [I] Using random values for input onnx::Cast_0
+[12/28/2023-20:30:49] [I] Created input binding for onnx::Cast_0 with dimensions 1x3x640x640
+[12/28/2023-20:30:49] [I] Using random values for output graph2_flat_predictions
+[12/28/2023-20:30:49] [I] Created output binding for graph2_flat_predictions with dimensions -1x57
+[12/28/2023-20:30:49] [I] Starting inference
+[12/28/2023-20:31:04] [I] Warmup completed 5 queries over 200 ms
+[12/28/2023-20:31:04] [I] Timing trace has 467 queries over 15.0803 s
+[12/28/2023-20:31:04] [I] 
+[12/28/2023-20:31:04] [I] === Trace details ===
+[12/28/2023-20:31:04] [I] Trace averages of 100 runs:
+[12/28/2023-20:31:04] [I] Average on 100 runs - GPU latency: 32.4935 ms - Host latency: 32.6124 ms (enqueue 32.5531 ms)
+[12/28/2023-20:31:04] [I] Average on 100 runs - GPU latency: 32.0289 ms - Host latency: 32.1442 ms (enqueue 32.092 ms)
+[12/28/2023-20:31:04] [I] Average on 100 runs - GPU latency: 31.9715 ms - Host latency: 32.0855 ms (enqueue 32.0299 ms)
+[12/28/2023-20:31:04] [I] Average on 100 runs - GPU latency: 32.1741 ms - Host latency: 32.2872 ms (enqueue 32.2448 ms)
+[12/28/2023-20:31:04] [I] 
+[12/28/2023-20:31:04] [I] === Performance summary ===
+[12/28/2023-20:31:04] [I] Throughput: 30.9676 qps
+[12/28/2023-20:31:04] [I] Latency: min = 29.5527 ms, max = 48.669 ms, mean = 32.255 ms, median = 31.8447 ms, percentile(90%) = 33.2435 ms, percentile(95%) = 35.3904 ms, percentile(99%) = 42.4307 ms
+[12/28/2023-20:31:04] [I] Enqueue Time: min = 29.5156 ms, max = 48.6032 ms, mean = 32.204 ms, median = 31.8164 ms, percentile(90%) = 32.9639 ms, percentile(95%) = 35.3633 ms, percentile(99%) = 42.3721 ms
+[12/28/2023-20:31:04] [I] H2D Latency: min = 0.0800781 ms, max = 0.116211 ms, mean = 0.0943801 ms, median = 0.0952148 ms, percentile(90%) = 0.0976562 ms, percentile(95%) = 0.0981445 ms, percentile(99%) = 0.107422 ms
+[12/28/2023-20:31:04] [I] GPU Compute Time: min = 29.4414 ms, max = 48.5475 ms, mean = 32.1403 ms, median = 31.7275 ms, percentile(90%) = 33.1393 ms, percentile(95%) = 35.2798 ms, percentile(99%) = 42.3066 ms
+[12/28/2023-20:31:04] [I] D2H Latency: min = 0.00292969 ms, max = 0.0655518 ms, mean = 0.0203297 ms, median = 0.0205078 ms, percentile(90%) = 0.0288086 ms, percentile(95%) = 0.03125 ms, percentile(99%) = 0.0375977 ms
+[12/28/2023-20:31:04] [I] Total Host Walltime: 15.0803 s
+[12/28/2023-20:31:04] [I] Total GPU Compute Time: 15.0095 s
+[12/28/2023-20:31:04] [I] Explanations of the performance metrics are printed in the verbose logs.
+[12/28/2023-20:31:04] [I] 
+&&&& PASSED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_l_int8.onnx --int8 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_l_int8.onnx.int8.engine

yolo_nas_pose_l_int8.onnx.usage.txt

@@ -0,0 +1,58 @@
+
+Model exported successfully to yolo_nas_pose_l_int8.onnx
+Model expects input image of shape [1, 3, 640, 640]
+Input image dtype is torch.uint8
+
+Exported model already contains preprocessing (normalization) step, so you don't need to do it manually.
+Preprocessing steps to be applied to input image are:
+Sequential(
+  (0): CastTensorTo(dtype=torch.float32)
+  (1): ChannelSelect(channels_indexes=tensor([2, 1, 0]))
+  (2): ApplyMeanStd(mean=[0.], scale=[255.])
+)
+
+
+Exported model contains postprocessing (NMS) step with the following parameters:
+    num_pre_nms_predictions=1000
+    max_predictions_per_image=10
+    nms_threshold=0.5
+    confidence_threshold=0.15
+    output_predictions_format=flat
+
+
+Exported model is in ONNX format and can be used with ONNXRuntime
+To run inference with ONNXRuntime, please use the following code snippet:
+
+    import onnxruntime
+    import numpy as np
+    session = onnxruntime.InferenceSession("yolo_nas_pose_l_int8.onnx", providers=["CUDAExecutionProvider", "CPUExecutionProvider"])
+    inputs = [o.name for o in session.get_inputs()]
+    outputs = [o.name for o in session.get_outputs()]
+
+    example_input_image = np.zeros((1, 3, 640, 640)).astype(np.uint8)
+    predictions = session.run(outputs, {inputs[0]: example_input_image})
+
+Exported model can also be used with TensorRT
+To run inference with TensorRT, please see TensorRT deployment documentation
+You can benchmark the model using the following code snippet:
+
+    trtexec --onnx=yolo_nas_pose_l_int8.onnx --int8 --avgRuns=100 --duration=15
+
+
+Exported model has predictions in flat format:
+
+# flat_predictions is a 2D array of [N,K] shape
+# Each row represents (image_index, x_min, y_min, x_max, y_max, confidence, joints...)
+# Please note all values are floats, so you have to convert them to integers if needed
+
+[flat_predictions] = predictions
+pred_bboxes = flat_predictions[:, 1:5]
+pred_scores = flat_predictions[:, 5]
+pred_joints = flat_predictions[:, 6:].reshape((len(pred_bboxes), -1, 3))
+for i in range(len(pred_bboxes)):
+    confidence = pred_scores[i]
+    x_min, y_min, x_max, y_max = pred_bboxes[i]
+    print(f"Detected pose with confidence={{confidence}}, x_min={{x_min}}, y_min={{y_min}}, x_max={{x_max}}, y_max={{y_max}}")
+    for joint_index, (x, y, confidence) in enumerate(pred_joints[i]):")
+        print(f"Joint {{joint_index}} has coordinates x={{x}}, y={{y}}, confidence={{confidence}}")
+

yolo_nas_pose_m_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7674809abd50d8acbab6500f1b7ad6cb0103539e6102066d7695160b9b0f8413
+size 78063545

yolo_nas_pose_m_fp16.onnx.best.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d694deef0e1f970fb285d669185a1984b38cb587324b7c380b896a02794431ae
+size 41498155

yolo_nas_pose_m_fp16.onnx.best.engine.err

@@ -0,0 +1,406 @@
+[12/28/2023-08:45:30] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-08:45:30] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-08:45:30] [W] [TRT] Calibrator is not being used. Users must provide dynamic range for all tensors that are not Int32 or Bool.
+[12/28/2023-09:13:06] [W] [TRT] Tactic Device request: 6262MB Available: 3108MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:13:07] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6262 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:13:07] [W] [TRT] Tactic Device request: 6262MB Available: 3107MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:13:07] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6262 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:13:07] [W] [TRT] Tactic Device request: 6262MB Available: 3106MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:13:07] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6262 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:13:09] [W] [TRT] Tactic Device request: 6251MB Available: 3131MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:13:09] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6251 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:13:09] [W] [TRT] Tactic Device request: 6251MB Available: 3131MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:13:09] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6251 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:21:25] [W] [TRT] Tactic Device request: 4711MB Available: 2436MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:21:25] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:21:25] [W] [TRT] Tactic Device request: 4711MB Available: 2436MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:21:26] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:21:26] [W] [TRT] Tactic Device request: 4711MB Available: 2437MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:21:26] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:21:27] [W] [TRT] Tactic Device request: 4701MB Available: 2436MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:21:27] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4701 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:21:27] [W] [TRT] Tactic Device request: 4701MB Available: 2436MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:21:27] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4701 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:21:47] [W] [TRT] Tactic Device request: 6275MB Available: 2435MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:21:47] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:21:47] [W] [TRT] Tactic Device request: 6275MB Available: 2435MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:21:47] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6275 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:21:47] [W] [TRT] Tactic Device request: 6275MB Available: 2435MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:21:47] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:21:49] [W] [TRT] Tactic Device request: 6270MB Available: 2436MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:21:49] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6270 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:21:49] [W] [TRT] Tactic Device request: 6270MB Available: 2436MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:21:49] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6270 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:32:33] [W] [TRT] Tactic Device request: 7056MB Available: 2270MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:32:33] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:32:33] [W] [TRT] Tactic Device request: 7056MB Available: 2270MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:32:33] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 7056 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:32:33] [W] [TRT] Tactic Device request: 7056MB Available: 2270MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:32:33] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:32:35] [W] [TRT] Tactic Device request: 7050MB Available: 2269MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:32:35] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7050 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:32:35] [W] [TRT] Tactic Device request: 7050MB Available: 2269MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:32:35] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 7050 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:32:56] [W] [TRT] Tactic Device request: 6354MB Available: 2266MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:32:56] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:32:56] [W] [TRT] Tactic Device request: 6354MB Available: 2266MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:32:56] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6354 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:32:56] [W] [TRT] Tactic Device request: 6354MB Available: 2267MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:32:56] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:32:58] [W] [TRT] Tactic Device request: 6351MB Available: 2267MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:32:58] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6351 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:32:58] [W] [TRT] Tactic Device request: 6351MB Available: 2267MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:32:58] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6351 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:47:49] [W] [TRT] Tactic Device request: 2394MB Available: 2107MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:47:50] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2394 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:47:50] [W] [TRT] Tactic Device request: 2394MB Available: 2107MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:47:50] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2394 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:47:50] [W] [TRT] Tactic Device request: 2392MB Available: 2105MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:47:50] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:47:51] [W] [TRT] Tactic Device request: 2392MB Available: 2105MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:47:51] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2392 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:47:51] [W] [TRT] Tactic Device request: 2392MB Available: 2105MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:47:51] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:47:52] [W] [TRT] Tactic Device request: 2391MB Available: 2105MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:47:52] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2391 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:47:52] [W] [TRT] Tactic Device request: 2391MB Available: 2105MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:47:52] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2391 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:47:52] [W] [TRT] Tactic Device request: 2390MB Available: 2105MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:47:52] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2390 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:47:52] [W] [TRT] Tactic Device request: 2390MB Available: 2105MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:47:52] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2390 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:48:10] [W] [TRT] Tactic Device request: 4906MB Available: 2087MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:48:10] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4906 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:48:10] [W] [TRT] Tactic Device request: 4906MB Available: 2087MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:48:10] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4906 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:48:10] [W] [TRT] Tactic Device request: 4906MB Available: 2087MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:48:10] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4906 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:48:12] [W] [TRT] Tactic Device request: 4905MB Available: 2088MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:48:12] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4905 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:48:12] [W] [TRT] Tactic Device request: 4905MB Available: 2088MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:48:12] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4905 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:12] [W] [TRT] Tactic Device request: 4906MB Available: 1978MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:12] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4906 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:12] [W] [TRT] Tactic Device request: 4906MB Available: 1978MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:12] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4906 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:12] [W] [TRT] Tactic Device request: 4906MB Available: 1978MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:12] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4906 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:13] [W] [TRT] Tactic Device request: 4905MB Available: 1977MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:14] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4905 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:14] [W] [TRT] Tactic Device request: 4905MB Available: 1977MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:14] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4905 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:16] [W] [TRT] Tactic Device request: 2457MB Available: 1978MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:16] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:16] [W] [TRT] Tactic Device request: 2457MB Available: 1977MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:16] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2457 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:16] [W] [TRT] Tactic Device request: 2457MB Available: 1978MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:16] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:18] [W] [TRT] Tactic Device request: 2456MB Available: 1978MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:18] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2456 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:18] [W] [TRT] Tactic Device request: 2456MB Available: 1978MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:18] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2456 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:46] [W] [TRT] Tactic Device request: 3587MB Available: 1952MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:46] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:46] [W] [TRT] Tactic Device request: 3587MB Available: 1952MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:46] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3587 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:46] [W] [TRT] Tactic Device request: 3587MB Available: 1952MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:46] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:47] [W] [TRT] Tactic Device request: 3585MB Available: 1951MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:47] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3585 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:47] [W] [TRT] Tactic Device request: 3585MB Available: 1951MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:47] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3585 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:49] [W] [TRT] Tactic Device request: 2385MB Available: 1949MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:49] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2385 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:49] [W] [TRT] Tactic Device request: 2385MB Available: 1949MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:49] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2385 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:49] [W] [TRT] Tactic Device request: 2385MB Available: 1949MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:49] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2385 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:50] [W] [TRT] Tactic Device request: 2384MB Available: 1950MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:50] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2384 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-09:56:50] [W] [TRT] Tactic Device request: 2384MB Available: 1950MB. Device memory is insufficient to use tactic.
+[12/28/2023-09:56:50] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2384 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:05:05] [W] [TRT] Tactic Device request: 3556MB Available: 1897MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:05:05] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:05:05] [W] [TRT] Tactic Device request: 3556MB Available: 1897MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:05:05] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3556 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:05:05] [W] [TRT] Tactic Device request: 3556MB Available: 1897MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:05:05] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:05:06] [W] [TRT] Tactic Device request: 3551MB Available: 1897MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:05:06] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3551 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:05:06] [W] [TRT] Tactic Device request: 3551MB Available: 1897MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:05:06] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3551 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:43] [W] [TRT] Tactic Device request: 2359MB Available: 1749MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:43] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2359 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:43] [W] [TRT] Tactic Device request: 2359MB Available: 1749MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:43] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2359 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:43] [W] [TRT] Tactic Device request: 2359MB Available: 1749MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:43] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2359 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:44] [W] [TRT] Tactic Device request: 2355MB Available: 1749MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:44] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2355 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:44] [W] [TRT] Tactic Device request: 2355MB Available: 1749MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:44] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2355 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:51] [W] [TRT] Tactic Device request: 2362MB Available: 1754MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:51] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2362 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:51] [W] [TRT] Tactic Device request: 2362MB Available: 1754MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:51] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2362 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:51] [W] [TRT] Tactic Device request: 2362MB Available: 1754MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:51] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2362 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:54] [W] [TRT] Tactic Device request: 2357MB Available: 1752MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:54] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2357 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:54] [W] [TRT] Tactic Device request: 2357MB Available: 1752MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:54] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2357 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:57] [W] [TRT] Tactic Device request: 2359MB Available: 1752MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:57] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2359 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:57] [W] [TRT] Tactic Device request: 2359MB Available: 1752MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:57] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2359 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:15:57] [W] [TRT] Tactic Device request: 2359MB Available: 1752MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:15:58] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2359 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:16:00] [W] [TRT] Tactic Device request: 2356MB Available: 1752MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:16:00] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2356 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:16:00] [W] [TRT] Tactic Device request: 2356MB Available: 1752MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:16:00] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2356 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:24:58] [W] [TRT] Tactic Device request: 3575MB Available: 2009MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:24:58] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3575 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:24:58] [W] [TRT] Tactic Device request: 3575MB Available: 2009MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:24:58] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3575 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:24:58] [W] [TRT] Tactic Device request: 3575MB Available: 2009MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:24:58] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3575 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:24:59] [W] [TRT] Tactic Device request: 3572MB Available: 2008MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:24:59] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3572 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:24:59] [W] [TRT] Tactic Device request: 3572MB Available: 2008MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:24:59] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3572 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:08] [W] [TRT] Tactic Device request: 2390MB Available: 1909MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:08] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2390 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:08] [W] [TRT] Tactic Device request: 2390MB Available: 1824MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:08] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2390 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:09] [W] [TRT] Tactic Device request: 2390MB Available: 1822MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:09] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2390 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:12] [W] [TRT] Tactic Device request: 2387MB Available: 1824MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:12] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2387 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:12] [W] [TRT] Tactic Device request: 2387MB Available: 1800MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:12] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2387 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:15] [W] [TRT] Tactic Device request: 2388MB Available: 1797MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:15] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2388 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:16] [W] [TRT] Tactic Device request: 2388MB Available: 1753MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:16] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2388 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:16] [W] [TRT] Tactic Device request: 2388MB Available: 1749MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:16] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2388 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:19] [W] [TRT] Tactic Device request: 2386MB Available: 1749MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:19] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2386 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:19] [W] [TRT] Tactic Device request: 2386MB Available: 1729MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:19] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2386 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:23] [W] [TRT] Tactic Device request: 4775MB Available: 1722MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:23] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4775 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:24] [W] [TRT] Tactic Device request: 4775MB Available: 1600MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:24] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4775 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:25] [W] [TRT] Tactic Device request: 4775MB Available: 1593MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:25] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4775 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:30] [W] [TRT] Tactic Device request: 4772MB Available: 1593MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:30] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4772 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:31] [W] [TRT] Tactic Device request: 4772MB Available: 1591MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:31] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4772 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:36] [W] [TRT] Tactic Device request: 4774MB Available: 1593MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:36] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4774 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:37] [W] [TRT] Tactic Device request: 4774MB Available: 1592MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:37] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4774 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:38] [W] [TRT] Tactic Device request: 4774MB Available: 1593MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:38] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4774 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:43] [W] [TRT] Tactic Device request: 4771MB Available: 1592MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:43] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4771 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:44] [W] [TRT] Tactic Device request: 4771MB Available: 1592MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:44] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4771 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:48] [W] [TRT] Tactic Device request: 1637MB Available: 1594MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:48] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 1637 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:49] [W] [TRT] Tactic Device request: 1637MB Available: 1594MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:49] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 1637 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:49] [W] [TRT] Tactic Device request: 1637MB Available: 1594MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:49] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 1637 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:50] [W] [TRT] Tactic Device request: 1636MB Available: 1592MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:50] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 1636 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:25:50] [W] [TRT] Tactic Device request: 1636MB Available: 1592MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:25:50] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 1636 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:26:03] [W] [TRT] Tactic Device request: 4774MB Available: 1593MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:26:03] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4774 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:26:04] [W] [TRT] Tactic Device request: 4774MB Available: 1591MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:26:04] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4774 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:26:05] [W] [TRT] Tactic Device request: 4774MB Available: 1589MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:26:05] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4774 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:26:10] [W] [TRT] Tactic Device request: 4771MB Available: 1591MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:26:10] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4771 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:26:11] [W] [TRT] Tactic Device request: 4771MB Available: 1588MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:26:11] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4771 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:30] [W] [TRT] Tactic Device request: 1638MB Available: 1396MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:30] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 1638 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:30] [W] [TRT] Tactic Device request: 1638MB Available: 1396MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:30] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 1638 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:31] [W] [TRT] Tactic Device request: 1637MB Available: 1395MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:31] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 1637 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:31] [W] [TRT] Tactic Device request: 1637MB Available: 1396MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:31] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 1637 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:33] [W] [TRT] Tactic Device request: 2454MB Available: 1396MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:33] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2454 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:33] [W] [TRT] Tactic Device request: 2454MB Available: 1396MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:33] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2454 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:33] [W] [TRT] Tactic Device request: 2454MB Available: 1397MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:33] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2454 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:34] [W] [TRT] Tactic Device request: 2453MB Available: 1397MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:34] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2453 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:34] [W] [TRT] Tactic Device request: 2453MB Available: 1397MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:34] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2453 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:37] [W] [TRT] Tactic Device request: 2463MB Available: 1427MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:37] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2463 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:38] [W] [TRT] Tactic Device request: 2463MB Available: 1390MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:38] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2463 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:39] [W] [TRT] Tactic Device request: 2463MB Available: 1388MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:39] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2463 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:43] [W] [TRT] Tactic Device request: 2462MB Available: 1596MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:43] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2462 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:44] [W] [TRT] Tactic Device request: 2462MB Available: 1379MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:44] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2462 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:49] [W] [TRT] Tactic Device request: 2463MB Available: 1378MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:49] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2463 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:49] [W] [TRT] Tactic Device request: 2463MB Available: 1376MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:49] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2463 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:50] [W] [TRT] Tactic Device request: 2463MB Available: 1376MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:50] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2463 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:54] [W] [TRT] Tactic Device request: 2462MB Available: 1375MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:54] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2462 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:36:55] [W] [TRT] Tactic Device request: 2462MB Available: 1375MB. Device memory is insufficient to use tactic.
+[12/28/2023-10:36:55] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2462 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-10:38:08] [W] * Throughput may be bound by Enqueue Time rather than GPU Compute and the GPU may be under-utilized.
+[12/28/2023-10:38:08] [W]   If not already in use, --useCudaGraph (utilize CUDA graphs where possible) may increase the throughput.
+[12/28/2023-10:38:08] [W] * GPU compute time is unstable, with coefficient of variance = 7.66665%.
+[12/28/2023-10:38:08] [W]   If not already in use, locking GPU clock frequency or adding --useSpinWait may improve the stability.

yolo_nas_pose_m_fp16.onnx.best.engine.log

@@ -0,0 +1,312 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_m_fp16.onnx --best --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_m_fp16.onnx.best.engine
+[12/28/2023-08:45:20] [I] === Model Options ===
+[12/28/2023-08:45:20] [I] Format: ONNX
+[12/28/2023-08:45:20] [I] Model: yolo_nas_pose_m_fp16.onnx
+[12/28/2023-08:45:20] [I] Output:
+[12/28/2023-08:45:20] [I] === Build Options ===
+[12/28/2023-08:45:20] [I] Max batch: explicit batch
+[12/28/2023-08:45:20] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-08:45:20] [I] minTiming: 1
+[12/28/2023-08:45:20] [I] avgTiming: 8
+[12/28/2023-08:45:20] [I] Precision: FP32+FP16+INT8
+[12/28/2023-08:45:20] [I] LayerPrecisions: 
+[12/28/2023-08:45:20] [I] Calibration: Dynamic
+[12/28/2023-08:45:20] [I] Refit: Disabled
+[12/28/2023-08:45:20] [I] Sparsity: Disabled
+[12/28/2023-08:45:20] [I] Safe mode: Disabled
+[12/28/2023-08:45:20] [I] DirectIO mode: Disabled
+[12/28/2023-08:45:20] [I] Restricted mode: Disabled
+[12/28/2023-08:45:20] [I] Build only: Disabled
+[12/28/2023-08:45:20] [I] Save engine: yolo_nas_pose_m_fp16.onnx.best.engine
+[12/28/2023-08:45:20] [I] Load engine: 
+[12/28/2023-08:45:20] [I] Profiling verbosity: 0
+[12/28/2023-08:45:20] [I] Tactic sources: Using default tactic sources
+[12/28/2023-08:45:20] [I] timingCacheMode: local
+[12/28/2023-08:45:20] [I] timingCacheFile: 
+[12/28/2023-08:45:20] [I] Heuristic: Disabled
+[12/28/2023-08:45:20] [I] Preview Features: Use default preview flags.
+[12/28/2023-08:45:20] [I] Input(s)s format: fp32:CHW
+[12/28/2023-08:45:20] [I] Output(s)s format: fp32:CHW
+[12/28/2023-08:45:20] [I] Input build shapes: model
+[12/28/2023-08:45:20] [I] Input calibration shapes: model
+[12/28/2023-08:45:20] [I] === System Options ===
+[12/28/2023-08:45:20] [I] Device: 0
+[12/28/2023-08:45:20] [I] DLACore: 
+[12/28/2023-08:45:20] [I] Plugins:
+[12/28/2023-08:45:20] [I] === Inference Options ===
+[12/28/2023-08:45:20] [I] Batch: Explicit
+[12/28/2023-08:45:20] [I] Input inference shapes: model
+[12/28/2023-08:45:20] [I] Iterations: 10
+[12/28/2023-08:45:20] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-08:45:20] [I] Sleep time: 0ms
+[12/28/2023-08:45:20] [I] Idle time: 0ms
+[12/28/2023-08:45:20] [I] Streams: 1
+[12/28/2023-08:45:20] [I] ExposeDMA: Disabled
+[12/28/2023-08:45:20] [I] Data transfers: Enabled
+[12/28/2023-08:45:20] [I] Spin-wait: Disabled
+[12/28/2023-08:45:20] [I] Multithreading: Disabled
+[12/28/2023-08:45:20] [I] CUDA Graph: Disabled
+[12/28/2023-08:45:20] [I] Separate profiling: Disabled
+[12/28/2023-08:45:20] [I] Time Deserialize: Disabled
+[12/28/2023-08:45:20] [I] Time Refit: Disabled
+[12/28/2023-08:45:20] [I] NVTX verbosity: 0
+[12/28/2023-08:45:20] [I] Persistent Cache Ratio: 0
+[12/28/2023-08:45:20] [I] Inputs:
+[12/28/2023-08:45:20] [I] === Reporting Options ===
+[12/28/2023-08:45:20] [I] Verbose: Disabled
+[12/28/2023-08:45:20] [I] Averages: 100 inferences
+[12/28/2023-08:45:20] [I] Percentiles: 90,95,99
+[12/28/2023-08:45:20] [I] Dump refittable layers:Disabled
+[12/28/2023-08:45:20] [I] Dump output: Disabled
+[12/28/2023-08:45:20] [I] Profile: Disabled
+[12/28/2023-08:45:20] [I] Export timing to JSON file: 
+[12/28/2023-08:45:20] [I] Export output to JSON file: 
+[12/28/2023-08:45:20] [I] Export profile to JSON file: 
+[12/28/2023-08:45:20] [I] 
+[12/28/2023-08:45:20] [I] === Device Information ===
+[12/28/2023-08:45:20] [I] Selected Device: Orin
+[12/28/2023-08:45:20] [I] Compute Capability: 8.7
+[12/28/2023-08:45:20] [I] SMs: 8
+[12/28/2023-08:45:20] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-08:45:20] [I] Device Global Memory: 7471 MiB
+[12/28/2023-08:45:20] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-08:45:20] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-08:45:20] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-08:45:20] [I] 
+[12/28/2023-08:45:20] [I] TensorRT version: 8.5.2
+[12/28/2023-08:45:24] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 2980 (MiB)
+[12/28/2023-08:45:29] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +284, now: CPU 574, GPU 3286 (MiB)
+[12/28/2023-08:45:29] [I] Start parsing network model
+[12/28/2023-08:45:30] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-08:45:30] [I] [TRT] Input filename:   yolo_nas_pose_m_fp16.onnx
+[12/28/2023-08:45:30] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-08:45:30] [I] [TRT] Opset version:    17
+[12/28/2023-08:45:30] [I] [TRT] Producer name:    pytorch
+[12/28/2023-08:45:30] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-08:45:30] [I] [TRT] Domain:           
+[12/28/2023-08:45:30] [I] [TRT] Model version:    0
+[12/28/2023-08:45:30] [I] [TRT] Doc string:       
+[12/28/2023-08:45:30] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-08:45:30] [I] Finish parsing network model
+[12/28/2023-08:45:31] [I] [TRT] ---------- Layers Running on DLA ----------
+[12/28/2023-08:45:31] [I] [TRT] ---------- Layers Running on GPU ----------
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation1]
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/pre_process/pre_process.0/Cast.../pre_process/pre_process.2/Mul]}
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 410) [Constant]
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 411) [Constant]
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 412) [Constant]
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stem/conv/rbr_reparam/Conv + /model/backbone/stem/conv/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/downsample/rbr_reparam/Conv + /model/backbone/stage1/downsample/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv2/conv/Conv + /model/backbone/stage1/blocks/conv2/act/Relu || /model/backbone/stage1/blocks/conv1/conv/Conv + /model/backbone/stage1/blocks/conv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 15) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 23) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv3/conv/Conv + /model/backbone/stage1/blocks/conv3/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_skip2/conv/Conv + /model/neck/neck2/reduce_skip2/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/downsample/rbr_reparam/Conv + /model/backbone/stage2/downsample/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/downsample/conv/Conv + /model/neck/neck2/downsample/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv2/conv/Conv + /model/backbone/stage2/blocks/conv2/act/Relu || /model/backbone/stage2/blocks/conv1/conv/Conv + /model/backbone/stage2/blocks/conv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 44) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 52) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 60) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv3/conv/Conv + /model/backbone/stage2/blocks/conv3/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip2/conv/Conv + /model/neck/neck1/reduce_skip2/act/Relu || /model/neck/neck2/reduce_skip1/conv/Conv + /model/neck/neck2/reduce_skip1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/downsample/rbr_reparam/Conv + /model/backbone/stage3/downsample/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/downsample/conv/Conv + /model/neck/neck1/downsample/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv2/conv/Conv + /model/backbone/stage3/blocks/conv2/act/Relu || /model/backbone/stage3/blocks/conv1/conv/Conv + /model/backbone/stage3/blocks/conv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 83) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 91) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 99) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 107) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.4.alpha + (Unnamed Layer* 115) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv3/conv/Conv + /model/backbone/stage3/blocks/conv3/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip1/conv/Conv + /model/neck/neck1/reduce_skip1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/downsample/rbr_reparam/Conv + /model/backbone/stage4/downsample/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv2/conv/Conv + /model/backbone/stage4/blocks/conv2/act/Relu || /model/backbone/stage4/blocks/conv1/conv/Conv + /model/backbone/stage4/blocks/conv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 134) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 142) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv3/conv/Conv + /model/backbone/stage4/blocks/conv3/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv1/conv/Conv + /model/backbone/context_module/cv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.2/MaxPool
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.1/MaxPool
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.0/MaxPool
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/backbone/context_module/cv1/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv2/conv/Conv + /model/backbone/context_module/cv2/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/conv/conv/Conv + /model/neck/neck1/conv/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck1/upsample/ConvTranspose
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_after_concat/conv/Conv + /model/neck/neck1/reduce_after_concat/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv2/conv/Conv + /model/neck/neck1/blocks/conv2/act/Relu || /model/neck/neck1/blocks/conv1/conv/Conv + /model/neck/neck1/blocks/conv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 171) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 179) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv3/conv/Conv + /model/neck/neck1/blocks/conv3/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/conv/conv/Conv + /model/neck/neck2/conv/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck2/upsample/ConvTranspose
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/reduce_skip1/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_after_concat/conv/Conv + /model/neck/neck2/reduce_after_concat/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv2/conv/Conv + /model/neck/neck2/blocks/conv2/act/Relu || /model/neck/neck2/blocks/conv1/conv/Conv + /model/neck/neck2/blocks/conv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 200) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 208) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 216) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv3/conv/Conv + /model/neck/neck2/blocks/conv3/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/bbox_stem/seq/conv/Conv + /model/heads/head1/bbox_stem/seq/act/Relu || /model/heads/head1/pose_stem/seq/conv/Conv + /model/heads/head1/pose_stem/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/conv/conv/Conv + /model/neck/neck3/conv/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head1/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head1/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head1/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv2/conv/Conv + /model/neck/neck3/blocks/conv2/act/Relu || /model/neck/neck3/blocks/conv1/conv/Conv + /model/neck/neck3/blocks/conv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/cls_pred/Conv
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_pred/Conv
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape + /model/heads/Transpose
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_pred/Conv
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 247) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 270) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv3/conv/Conv + /model/neck/neck3/blocks/conv3/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_stem/seq/conv/Conv + /model/heads/head2/pose_stem/seq/act/Relu || /model/heads/head2/bbox_stem/seq/conv/Conv + /model/heads/head2/bbox_stem/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/conv/conv/Conv + /model/neck/neck4/conv/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head2/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head2/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head2/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv2/conv/Conv + /model/neck/neck4/blocks/conv2/act/Relu || /model/neck/neck4/blocks/conv1/conv/Conv + /model/neck/neck4/blocks/conv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/cls_pred/Conv
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_pred/Conv
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_4 + /model/heads/Transpose_3
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_pred/Conv
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_1
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 301) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_1
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 324) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.2.alpha + (Unnamed Layer* 332) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv3/conv/Conv + /model/neck/neck4/blocks/conv3/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/bbox_stem/seq/conv/Conv + /model/heads/head3/bbox_stem/seq/act/Relu || /model/heads/head3/pose_stem/seq/conv/Conv + /model/heads/head3/pose_stem/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head3/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head3/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head3/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/cls_pred/Conv
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_pred/Conv
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_8 + /model/heads/Transpose_6
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.2/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.2/seq/act/Relu
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_2
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_pred/Conv
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_2
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice_1...cast_boxes_to_fp32]}
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] NMS: batched_nms_26
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] DEVICE_TO_SHAPE_HOST: (Unnamed Layer* 414) [NMS]_1_output[DevicetoShapeHostCopy]
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation2]
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice...graph2_/Concat_5]}
+[12/28/2023-08:45:31] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation3]
+[12/28/2023-08:45:44] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +534, GPU +400, now: CPU 1196, GPU 3820 (MiB)
+[12/28/2023-08:45:46] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +82, GPU +70, now: CPU 1278, GPU 3890 (MiB)
+[12/28/2023-08:45:46] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
+[12/28/2023-10:37:30] [I] [TRT] Total Activation Memory: 7941309952
+[12/28/2023-10:37:30] [I] [TRT] Detected 1 inputs and 1 output network tensors.
+[12/28/2023-10:37:43] [I] [TRT] Total Host Persistent Memory: 294816
+[12/28/2023-10:37:43] [I] [TRT] Total Device Persistent Memory: 38912
+[12/28/2023-10:37:43] [I] [TRT] Total Scratch Memory: 134217728
+[12/28/2023-10:37:43] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 54 MiB, GPU 2398 MiB
+[12/28/2023-10:37:43] [I] [TRT] [BlockAssignment] Started assigning block shifts. This will take 157 steps to complete.
+[12/28/2023-10:37:43] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 76.003ms to assign 14 blocks to 157 nodes requiring 144914944 bytes.
+[12/28/2023-10:37:43] [I] [TRT] Total Activation Memory: 144914944
+[12/28/2023-10:37:50] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU -1, now: CPU 1667, GPU 5526 (MiB)
+[12/28/2023-10:37:50] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +38, GPU +64, now: CPU 38, GPU 64 (MiB)
+[12/28/2023-10:37:51] [I] Engine built in 6750.81 sec.
+[12/28/2023-10:37:52] [I] [TRT] Loaded engine size: 39 MiB
+[12/28/2023-10:37:52] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1284, GPU 5348 (MiB)
+[12/28/2023-10:37:52] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +37, now: CPU 0, GPU 37 (MiB)
+[12/28/2023-10:37:52] [I] Engine deserialized in 0.265686 sec.
+[12/28/2023-10:37:52] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1284, GPU 5348 (MiB)
+[12/28/2023-10:37:52] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +138, now: CPU 0, GPU 175 (MiB)
+[12/28/2023-10:37:52] [I] Setting persistentCacheLimit to 0 bytes.
+[12/28/2023-10:37:52] [I] Using random values for input onnx::Cast_0
+[12/28/2023-10:37:52] [I] Created input binding for onnx::Cast_0 with dimensions 1x3x640x640
+[12/28/2023-10:37:52] [I] Using random values for output graph2_flat_predictions
+[12/28/2023-10:37:52] [I] Created output binding for graph2_flat_predictions with dimensions -1x57
+[12/28/2023-10:37:52] [I] Starting inference
+[12/28/2023-10:38:08] [I] Warmup completed 2 queries over 200 ms
+[12/28/2023-10:38:08] [I] Timing trace has 875 queries over 15.0204 s
+[12/28/2023-10:38:08] [I] 
+[12/28/2023-10:38:08] [I] === Trace details ===
+[12/28/2023-10:38:08] [I] Trace averages of 100 runs:
+[12/28/2023-10:38:08] [I] Average on 100 runs - GPU latency: 17.3015 ms - Host latency: 17.42 ms (enqueue 17.373 ms)
+[12/28/2023-10:38:08] [I] Average on 100 runs - GPU latency: 16.7848 ms - Host latency: 16.8974 ms (enqueue 16.8579 ms)
+[12/28/2023-10:38:08] [I] Average on 100 runs - GPU latency: 16.7202 ms - Host latency: 16.8311 ms (enqueue 16.7917 ms)
+[12/28/2023-10:38:08] [I] Average on 100 runs - GPU latency: 16.7189 ms - Host latency: 16.8301 ms (enqueue 16.7925 ms)
+[12/28/2023-10:38:08] [I] Average on 100 runs - GPU latency: 16.8722 ms - Host latency: 16.9814 ms (enqueue 16.939 ms)
+[12/28/2023-10:38:08] [I] Average on 100 runs - GPU latency: 17.0499 ms - Host latency: 17.165 ms (enqueue 17.1147 ms)
+[12/28/2023-10:38:08] [I] Average on 100 runs - GPU latency: 17.4353 ms - Host latency: 17.5548 ms (enqueue 17.5031 ms)
+[12/28/2023-10:38:08] [I] Average on 100 runs - GPU latency: 17.2635 ms - Host latency: 17.3821 ms (enqueue 17.328 ms)
+[12/28/2023-10:38:08] [I] 
+[12/28/2023-10:38:08] [I] === Performance summary ===
+[12/28/2023-10:38:08] [I] Throughput: 58.254 qps
+[12/28/2023-10:38:08] [I] Latency: min = 15.8867 ms, max = 26.5801 ms, mean = 17.1335 ms, median = 16.9814 ms, percentile(90%) = 17.8691 ms, percentile(95%) = 18.4963 ms, percentile(99%) = 24.3384 ms
+[12/28/2023-10:38:08] [I] Enqueue Time: min = 15.8533 ms, max = 26.5361 ms, mean = 17.0885 ms, median = 16.9271 ms, percentile(90%) = 17.8125 ms, percentile(95%) = 18.4688 ms, percentile(99%) = 23.7695 ms
+[12/28/2023-10:38:08] [I] H2D Latency: min = 0.0800781 ms, max = 0.148483 ms, mean = 0.0972059 ms, median = 0.0976562 ms, percentile(90%) = 0.100464 ms, percentile(95%) = 0.100586 ms, percentile(99%) = 0.110596 ms
+[12/28/2023-10:38:08] [I] GPU Compute Time: min = 15.7729 ms, max = 26.4624 ms, mean = 17.019 ms, median = 16.8655 ms, percentile(90%) = 17.7568 ms, percentile(95%) = 18.3837 ms, percentile(99%) = 24.2227 ms
+[12/28/2023-10:38:08] [I] D2H Latency: min = 0.00292969 ms, max = 0.0673828 ms, mean = 0.0172236 ms, median = 0.0146484 ms, percentile(90%) = 0.0263672 ms, percentile(95%) = 0.0283203 ms, percentile(99%) = 0.0407715 ms
+[12/28/2023-10:38:08] [I] Total Host Walltime: 15.0204 s
+[12/28/2023-10:38:08] [I] Total GPU Compute Time: 14.8917 s
+[12/28/2023-10:38:08] [I] Explanations of the performance metrics are printed in the verbose logs.
+[12/28/2023-10:38:08] [I] 
+&&&& PASSED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_m_fp16.onnx --best --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_m_fp16.onnx.best.engine

yolo_nas_pose_m_fp16.onnx.engine.err

@@ -0,0 +1,8 @@
+[12/28/2023-07:47:56] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-07:47:56] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-07:47:57] [E] Error[4]: [network.cpp::validate::2925] Error Code 4: Internal Error (fp16 precision has been set for a layer or layer output, but fp16 is not configured in the builder)
+[12/28/2023-07:47:57] [E] Error[2]: [builder.cpp::buildSerializedNetwork::751] Error Code 2: Internal Error (Assertion engine != nullptr failed. )
+[12/28/2023-07:47:57] [E] Engine could not be created from network
+[12/28/2023-07:47:57] [E] Building engine failed
+[12/28/2023-07:47:57] [E] Failed to create engine from model or file.
+[12/28/2023-07:47:57] [E] Engine set up failed

yolo_nas_pose_m_fp16.onnx.engine.log

@@ -0,0 +1,91 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_m_fp16.onnx --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_m_fp16.onnx.engine
+[12/28/2023-07:47:46] [I] === Model Options ===
+[12/28/2023-07:47:46] [I] Format: ONNX
+[12/28/2023-07:47:46] [I] Model: yolo_nas_pose_m_fp16.onnx
+[12/28/2023-07:47:46] [I] Output:
+[12/28/2023-07:47:46] [I] === Build Options ===
+[12/28/2023-07:47:46] [I] Max batch: explicit batch
+[12/28/2023-07:47:46] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-07:47:46] [I] minTiming: 1
+[12/28/2023-07:47:46] [I] avgTiming: 8
+[12/28/2023-07:47:46] [I] Precision: FP32
+[12/28/2023-07:47:46] [I] LayerPrecisions: 
+[12/28/2023-07:47:46] [I] Calibration: 
+[12/28/2023-07:47:46] [I] Refit: Disabled
+[12/28/2023-07:47:46] [I] Sparsity: Disabled
+[12/28/2023-07:47:46] [I] Safe mode: Disabled
+[12/28/2023-07:47:46] [I] DirectIO mode: Disabled
+[12/28/2023-07:47:46] [I] Restricted mode: Disabled
+[12/28/2023-07:47:46] [I] Build only: Disabled
+[12/28/2023-07:47:46] [I] Save engine: yolo_nas_pose_m_fp16.onnx.engine
+[12/28/2023-07:47:46] [I] Load engine: 
+[12/28/2023-07:47:46] [I] Profiling verbosity: 0
+[12/28/2023-07:47:46] [I] Tactic sources: Using default tactic sources
+[12/28/2023-07:47:46] [I] timingCacheMode: local
+[12/28/2023-07:47:46] [I] timingCacheFile: 
+[12/28/2023-07:47:46] [I] Heuristic: Disabled
+[12/28/2023-07:47:46] [I] Preview Features: Use default preview flags.
+[12/28/2023-07:47:46] [I] Input(s)s format: fp32:CHW
+[12/28/2023-07:47:46] [I] Output(s)s format: fp32:CHW
+[12/28/2023-07:47:46] [I] Input build shapes: model
+[12/28/2023-07:47:46] [I] Input calibration shapes: model
+[12/28/2023-07:47:46] [I] === System Options ===
+[12/28/2023-07:47:46] [I] Device: 0
+[12/28/2023-07:47:46] [I] DLACore: 
+[12/28/2023-07:47:46] [I] Plugins:
+[12/28/2023-07:47:46] [I] === Inference Options ===
+[12/28/2023-07:47:46] [I] Batch: Explicit
+[12/28/2023-07:47:46] [I] Input inference shapes: model
+[12/28/2023-07:47:46] [I] Iterations: 10
+[12/28/2023-07:47:46] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-07:47:46] [I] Sleep time: 0ms
+[12/28/2023-07:47:46] [I] Idle time: 0ms
+[12/28/2023-07:47:46] [I] Streams: 1
+[12/28/2023-07:47:46] [I] ExposeDMA: Disabled
+[12/28/2023-07:47:46] [I] Data transfers: Enabled
+[12/28/2023-07:47:46] [I] Spin-wait: Disabled
+[12/28/2023-07:47:46] [I] Multithreading: Disabled
+[12/28/2023-07:47:46] [I] CUDA Graph: Disabled
+[12/28/2023-07:47:46] [I] Separate profiling: Disabled
+[12/28/2023-07:47:46] [I] Time Deserialize: Disabled
+[12/28/2023-07:47:46] [I] Time Refit: Disabled
+[12/28/2023-07:47:46] [I] NVTX verbosity: 0
+[12/28/2023-07:47:46] [I] Persistent Cache Ratio: 0
+[12/28/2023-07:47:46] [I] Inputs:
+[12/28/2023-07:47:46] [I] === Reporting Options ===
+[12/28/2023-07:47:46] [I] Verbose: Disabled
+[12/28/2023-07:47:46] [I] Averages: 100 inferences
+[12/28/2023-07:47:46] [I] Percentiles: 90,95,99
+[12/28/2023-07:47:46] [I] Dump refittable layers:Disabled
+[12/28/2023-07:47:46] [I] Dump output: Disabled
+[12/28/2023-07:47:46] [I] Profile: Disabled
+[12/28/2023-07:47:46] [I] Export timing to JSON file: 
+[12/28/2023-07:47:46] [I] Export output to JSON file: 
+[12/28/2023-07:47:46] [I] Export profile to JSON file: 
+[12/28/2023-07:47:46] [I] 
+[12/28/2023-07:47:46] [I] === Device Information ===
+[12/28/2023-07:47:46] [I] Selected Device: Orin
+[12/28/2023-07:47:46] [I] Compute Capability: 8.7
+[12/28/2023-07:47:46] [I] SMs: 8
+[12/28/2023-07:47:46] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-07:47:46] [I] Device Global Memory: 7471 MiB
+[12/28/2023-07:47:46] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-07:47:46] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-07:47:46] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-07:47:46] [I] 
+[12/28/2023-07:47:46] [I] TensorRT version: 8.5.2
+[12/28/2023-07:47:51] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 3024 (MiB)
+[12/28/2023-07:47:55] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +284, now: CPU 574, GPU 3327 (MiB)
+[12/28/2023-07:47:55] [I] Start parsing network model
+[12/28/2023-07:47:56] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-07:47:56] [I] [TRT] Input filename:   yolo_nas_pose_m_fp16.onnx
+[12/28/2023-07:47:56] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-07:47:56] [I] [TRT] Opset version:    17
+[12/28/2023-07:47:56] [I] [TRT] Producer name:    pytorch
+[12/28/2023-07:47:56] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-07:47:56] [I] [TRT] Domain:           
+[12/28/2023-07:47:56] [I] [TRT] Model version:    0
+[12/28/2023-07:47:56] [I] [TRT] Doc string:       
+[12/28/2023-07:47:56] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-07:47:57] [I] Finish parsing network model
+&&&& FAILED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_m_fp16.onnx --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_m_fp16.onnx.engine

yolo_nas_pose_m_fp16.onnx.fp16.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b66cc2f44220a42e474a86ccc143cd0982f5549e47a979486545e1657fbbc8
+size 79706512

yolo_nas_pose_m_fp16.onnx.fp16.engine.err

@@ -0,0 +1,348 @@
+[12/28/2023-07:48:01] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-07:48:01] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-07:52:40] [W] [TRT] Tactic Device request: 6262MB Available: 3207MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:52:40] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6262 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:52:40] [W] [TRT] Tactic Device request: 6262MB Available: 3207MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:52:40] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6262 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:52:40] [W] [TRT] Tactic Device request: 6262MB Available: 3207MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:52:40] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6262 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:52:42] [W] [TRT] Tactic Device request: 6251MB Available: 3210MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:52:42] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6251 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:52:42] [W] [TRT] Tactic Device request: 6251MB Available: 3210MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:52:43] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6251 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:57:47] [W] [TRT] Tactic Device request: 4711MB Available: 2426MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:57:47] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:57:47] [W] [TRT] Tactic Device request: 4711MB Available: 2426MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:57:47] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4711 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:57:47] [W] [TRT] Tactic Device request: 4711MB Available: 2426MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:57:47] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4711 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:57:49] [W] [TRT] Tactic Device request: 4701MB Available: 2426MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:57:49] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4701 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:57:49] [W] [TRT] Tactic Device request: 4701MB Available: 2426MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:57:49] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4701 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:58:04] [W] [TRT] Tactic Device request: 6275MB Available: 2426MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:58:04] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:58:05] [W] [TRT] Tactic Device request: 6275MB Available: 2426MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:58:05] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6275 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:58:05] [W] [TRT] Tactic Device request: 6275MB Available: 2426MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:58:05] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6275 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:58:06] [W] [TRT] Tactic Device request: 6270MB Available: 2425MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:58:06] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6270 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-07:58:06] [W] [TRT] Tactic Device request: 6270MB Available: 2426MB. Device memory is insufficient to use tactic.
+[12/28/2023-07:58:06] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6270 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:04:38] [W] [TRT] Tactic Device request: 7056MB Available: 2305MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:04:38] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:04:38] [W] [TRT] Tactic Device request: 7056MB Available: 2305MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:04:38] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 7056 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:04:38] [W] [TRT] Tactic Device request: 7056MB Available: 2302MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:04:38] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 7056 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:04:40] [W] [TRT] Tactic Device request: 7050MB Available: 2302MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:04:40] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 7050 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:04:40] [W] [TRT] Tactic Device request: 7050MB Available: 2302MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:04:40] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 7050 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:04:56] [W] [TRT] Tactic Device request: 6354MB Available: 2299MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:04:56] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:04:56] [W] [TRT] Tactic Device request: 6354MB Available: 2299MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:04:56] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 6354 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:04:57] [W] [TRT] Tactic Device request: 6354MB Available: 2308MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:04:57] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 6354 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:04:58] [W] [TRT] Tactic Device request: 6351MB Available: 2305MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:04:58] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 6351 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:04:58] [W] [TRT] Tactic Device request: 6351MB Available: 2306MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:04:58] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 6351 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:13:43] [W] [TRT] Tactic Device request: 2394MB Available: 2369MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:13:43] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2394 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:13:43] [W] [TRT] Tactic Device request: 2394MB Available: 2369MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:13:43] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2394 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:13:44] [W] [TRT] Tactic Device request: 2392MB Available: 2366MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:13:44] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:13:44] [W] [TRT] Tactic Device request: 2392MB Available: 2366MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:13:44] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2392 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:13:44] [W] [TRT] Tactic Device request: 2392MB Available: 2366MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:13:44] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2392 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:13:45] [W] [TRT] Tactic Device request: 2391MB Available: 2367MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:13:45] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2391 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:13:45] [W] [TRT] Tactic Device request: 2391MB Available: 2367MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:13:45] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2391 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:13:45] [W] [TRT] Tactic Device request: 2390MB Available: 2367MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:13:45] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2390 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:13:45] [W] [TRT] Tactic Device request: 2390MB Available: 2365MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:13:45] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2390 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:13:59] [W] [TRT] Tactic Device request: 4906MB Available: 2349MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:13:59] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4906 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:13:59] [W] [TRT] Tactic Device request: 4906MB Available: 2348MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:13:59] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4906 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:14:00] [W] [TRT] Tactic Device request: 4906MB Available: 2349MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:14:00] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 4906 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:14:01] [W] [TRT] Tactic Device request: 4905MB Available: 2337MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:14:01] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4905 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:14:01] [W] [TRT] Tactic Device request: 4905MB Available: 2336MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:14:01] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 4905 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:18:56] [W] [TRT] Tactic Device request: 2457MB Available: 2273MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:18:56] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:18:56] [W] [TRT] Tactic Device request: 2457MB Available: 2273MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:18:56] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2457 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:18:56] [W] [TRT] Tactic Device request: 2457MB Available: 2273MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:18:56] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2457 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:18:57] [W] [TRT] Tactic Device request: 2456MB Available: 2272MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:18:57] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2456 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:18:57] [W] [TRT] Tactic Device request: 2456MB Available: 2272MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:18:57] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2456 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:19:19] [W] [TRT] Tactic Device request: 3587MB Available: 2263MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:19:19] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:19:19] [W] [TRT] Tactic Device request: 3587MB Available: 2263MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:19:19] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3587 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:19:19] [W] [TRT] Tactic Device request: 3587MB Available: 2263MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:19:19] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3587 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:19:20] [W] [TRT] Tactic Device request: 3585MB Available: 2263MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:19:20] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3585 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:19:20] [W] [TRT] Tactic Device request: 3585MB Available: 2263MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:19:20] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3585 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:19:21] [W] [TRT] Tactic Device request: 2385MB Available: 2264MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:19:21] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2385 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:19:21] [W] [TRT] Tactic Device request: 2385MB Available: 2264MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:19:21] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2385 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:19:21] [W] [TRT] Tactic Device request: 2385MB Available: 2264MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:19:21] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2385 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:19:22] [W] [TRT] Tactic Device request: 2384MB Available: 2262MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:19:22] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2384 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:19:22] [W] [TRT] Tactic Device request: 2384MB Available: 2262MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:19:22] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2384 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:24:28] [W] [TRT] Tactic Device request: 3556MB Available: 2243MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:24:28] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:24:28] [W] [TRT] Tactic Device request: 3556MB Available: 2243MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:24:28] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3556 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:24:28] [W] [TRT] Tactic Device request: 3556MB Available: 2243MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:24:28] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3556 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:24:29] [W] [TRT] Tactic Device request: 3551MB Available: 2243MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:24:30] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3551 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:24:30] [W] [TRT] Tactic Device request: 3551MB Available: 2243MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:24:30] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3551 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:02] [W] [TRT] Tactic Device request: 2359MB Available: 2128MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:02] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2359 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:02] [W] [TRT] Tactic Device request: 2359MB Available: 2128MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:02] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2359 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:02] [W] [TRT] Tactic Device request: 2359MB Available: 2128MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:02] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2359 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:03] [W] [TRT] Tactic Device request: 2355MB Available: 2129MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:03] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2355 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:03] [W] [TRT] Tactic Device request: 2355MB Available: 2129MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:03] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2355 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:07] [W] [TRT] Tactic Device request: 2362MB Available: 2128MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:07] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2362 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:08] [W] [TRT] Tactic Device request: 2362MB Available: 2128MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:08] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2362 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:08] [W] [TRT] Tactic Device request: 2362MB Available: 2128MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:08] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2362 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:10] [W] [TRT] Tactic Device request: 2357MB Available: 2129MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:10] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2357 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:11] [W] [TRT] Tactic Device request: 2357MB Available: 2129MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:11] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2357 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:12] [W] [TRT] Tactic Device request: 2359MB Available: 2129MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:12] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2359 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:13] [W] [TRT] Tactic Device request: 2359MB Available: 2128MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:13] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2359 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:13] [W] [TRT] Tactic Device request: 2359MB Available: 2128MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:13] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2359 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:15] [W] [TRT] Tactic Device request: 2356MB Available: 2128MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:16] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2356 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:31:16] [W] [TRT] Tactic Device request: 2356MB Available: 2128MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:31:16] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2356 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:36:53] [W] [TRT] Tactic Device request: 3575MB Available: 2474MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:36:53] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3575 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:36:53] [W] [TRT] Tactic Device request: 3575MB Available: 2475MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:36:53] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 3575 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:36:53] [W] [TRT] Tactic Device request: 3575MB Available: 2475MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:36:53] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 3575 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:36:54] [W] [TRT] Tactic Device request: 3572MB Available: 2475MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:36:54] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 3572 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:36:54] [W] [TRT] Tactic Device request: 3572MB Available: 2475MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:36:54] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 3572 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:00] [W] [TRT] Tactic Device request: 2390MB Available: 2347MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:00] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2390 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:00] [W] [TRT] Tactic Device request: 2390MB Available: 2269MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:00] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2390 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:01] [W] [TRT] Tactic Device request: 2390MB Available: 2265MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:01] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2390 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:04] [W] [TRT] Tactic Device request: 2387MB Available: 2263MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:04] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2387 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:04] [W] [TRT] Tactic Device request: 2387MB Available: 2239MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:04] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2387 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:06] [W] [TRT] Tactic Device request: 2388MB Available: 2234MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:06] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2388 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:07] [W] [TRT] Tactic Device request: 2388MB Available: 2205MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:07] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2388 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:07] [W] [TRT] Tactic Device request: 2388MB Available: 2203MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:07] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2388 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:10] [W] [TRT] Tactic Device request: 2386MB Available: 2203MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:10] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2386 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:10] [W] [TRT] Tactic Device request: 2386MB Available: 2176MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:10] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2386 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:13] [W] [TRT] Tactic Device request: 4775MB Available: 2174MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:13] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4775 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:13] [W] [TRT] Tactic Device request: 4775MB Available: 2034MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:13] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4775 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:14] [W] [TRT] Tactic Device request: 4775MB Available: 2034MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:14] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4775 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:19] [W] [TRT] Tactic Device request: 4772MB Available: 2034MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:19] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4772 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:20] [W] [TRT] Tactic Device request: 4772MB Available: 2034MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:20] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4772 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:24] [W] [TRT] Tactic Device request: 4774MB Available: 2033MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:24] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4774 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:25] [W] [TRT] Tactic Device request: 4774MB Available: 2033MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:25] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 4774 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:26] [W] [TRT] Tactic Device request: 4774MB Available: 2034MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:26] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 4774 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:31] [W] [TRT] Tactic Device request: 4771MB Available: 2034MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:31] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 4771 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:37:31] [W] [TRT] Tactic Device request: 4771MB Available: 2034MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:37:32] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 4771 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:43:58] [W] [TRT] Tactic Device request: 2454MB Available: 1908MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:43:58] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2454 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:43:58] [W] [TRT] Tactic Device request: 2454MB Available: 1908MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:43:58] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2454 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:43:58] [W] [TRT] Tactic Device request: 2454MB Available: 1907MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:43:58] [W] [TRT] Skipping tactic 13 due to insufficient memory on requested size of 2454 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:43:59] [W] [TRT] Tactic Device request: 2453MB Available: 1907MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:43:59] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2453 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:43:59] [W] [TRT] Tactic Device request: 2453MB Available: 1906MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:43:59] [W] [TRT] Skipping tactic 7 due to insufficient memory on requested size of 2453 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:44:01] [W] [TRT] Tactic Device request: 2463MB Available: 1901MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:44:01] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2463 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:44:02] [W] [TRT] Tactic Device request: 2463MB Available: 1909MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:44:02] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2463 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:44:03] [W] [TRT] Tactic Device request: 2463MB Available: 1910MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:44:03] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2463 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:44:07] [W] [TRT] Tactic Device request: 2462MB Available: 1898MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:44:07] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2462 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:44:07] [W] [TRT] Tactic Device request: 2462MB Available: 1898MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:44:07] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2462 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:44:10] [W] [TRT] Tactic Device request: 2463MB Available: 1898MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:44:10] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2463 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:44:11] [W] [TRT] Tactic Device request: 2463MB Available: 1898MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:44:11] [W] [TRT] Skipping tactic 9 due to insufficient memory on requested size of 2463 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:44:12] [W] [TRT] Tactic Device request: 2463MB Available: 1898MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:44:12] [W] [TRT] Skipping tactic 15 due to insufficient memory on requested size of 2463 detected for tactic 0x0000000000000074.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:44:16] [W] [TRT] Tactic Device request: 2462MB Available: 1899MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:44:16] [W] [TRT] Skipping tactic 3 due to insufficient memory on requested size of 2462 detected for tactic 0x0000000000000004.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:44:17] [W] [TRT] Tactic Device request: 2462MB Available: 1898MB. Device memory is insufficient to use tactic.
+[12/28/2023-08:44:17] [W] [TRT] Skipping tactic 8 due to insufficient memory on requested size of 2462 detected for tactic 0x000000000000003c.
+Try decreasing the workspace size with IBuilderConfig::setMemoryPoolLimit().
+[12/28/2023-08:45:16] [W] * Throughput may be bound by Enqueue Time rather than GPU Compute and the GPU may be under-utilized.
+[12/28/2023-08:45:16] [W]   If not already in use, --useCudaGraph (utilize CUDA graphs where possible) may increase the throughput.
+[12/28/2023-08:45:16] [W] * GPU compute time is unstable, with coefficient of variance = 2.78032%.
+[12/28/2023-08:45:16] [W]   If not already in use, locking GPU clock frequency or adding --useSpinWait may improve the stability.

yolo_nas_pose_m_fp16.onnx.fp16.engine.log

@@ -0,0 +1,309 @@
+&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_m_fp16.onnx --fp16 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_m_fp16.onnx.fp16.engine
+[12/28/2023-07:47:57] [I] === Model Options ===
+[12/28/2023-07:47:57] [I] Format: ONNX
+[12/28/2023-07:47:57] [I] Model: yolo_nas_pose_m_fp16.onnx
+[12/28/2023-07:47:57] [I] Output:
+[12/28/2023-07:47:57] [I] === Build Options ===
+[12/28/2023-07:47:57] [I] Max batch: explicit batch
+[12/28/2023-07:47:57] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
+[12/28/2023-07:47:57] [I] minTiming: 1
+[12/28/2023-07:47:57] [I] avgTiming: 8
+[12/28/2023-07:47:57] [I] Precision: FP32+FP16
+[12/28/2023-07:47:57] [I] LayerPrecisions: 
+[12/28/2023-07:47:57] [I] Calibration: 
+[12/28/2023-07:47:57] [I] Refit: Disabled
+[12/28/2023-07:47:57] [I] Sparsity: Disabled
+[12/28/2023-07:47:57] [I] Safe mode: Disabled
+[12/28/2023-07:47:57] [I] DirectIO mode: Disabled
+[12/28/2023-07:47:57] [I] Restricted mode: Disabled
+[12/28/2023-07:47:57] [I] Build only: Disabled
+[12/28/2023-07:47:57] [I] Save engine: yolo_nas_pose_m_fp16.onnx.fp16.engine
+[12/28/2023-07:47:57] [I] Load engine: 
+[12/28/2023-07:47:57] [I] Profiling verbosity: 0
+[12/28/2023-07:47:57] [I] Tactic sources: Using default tactic sources
+[12/28/2023-07:47:57] [I] timingCacheMode: local
+[12/28/2023-07:47:57] [I] timingCacheFile: 
+[12/28/2023-07:47:57] [I] Heuristic: Disabled
+[12/28/2023-07:47:57] [I] Preview Features: Use default preview flags.
+[12/28/2023-07:47:57] [I] Input(s)s format: fp32:CHW
+[12/28/2023-07:47:57] [I] Output(s)s format: fp32:CHW
+[12/28/2023-07:47:57] [I] Input build shapes: model
+[12/28/2023-07:47:57] [I] Input calibration shapes: model
+[12/28/2023-07:47:57] [I] === System Options ===
+[12/28/2023-07:47:57] [I] Device: 0
+[12/28/2023-07:47:57] [I] DLACore: 
+[12/28/2023-07:47:57] [I] Plugins:
+[12/28/2023-07:47:57] [I] === Inference Options ===
+[12/28/2023-07:47:57] [I] Batch: Explicit
+[12/28/2023-07:47:57] [I] Input inference shapes: model
+[12/28/2023-07:47:57] [I] Iterations: 10
+[12/28/2023-07:47:57] [I] Duration: 15s (+ 200ms warm up)
+[12/28/2023-07:47:57] [I] Sleep time: 0ms
+[12/28/2023-07:47:57] [I] Idle time: 0ms
+[12/28/2023-07:47:57] [I] Streams: 1
+[12/28/2023-07:47:57] [I] ExposeDMA: Disabled
+[12/28/2023-07:47:57] [I] Data transfers: Enabled
+[12/28/2023-07:47:57] [I] Spin-wait: Disabled
+[12/28/2023-07:47:57] [I] Multithreading: Disabled
+[12/28/2023-07:47:57] [I] CUDA Graph: Disabled
+[12/28/2023-07:47:57] [I] Separate profiling: Disabled
+[12/28/2023-07:47:57] [I] Time Deserialize: Disabled
+[12/28/2023-07:47:57] [I] Time Refit: Disabled
+[12/28/2023-07:47:57] [I] NVTX verbosity: 0
+[12/28/2023-07:47:57] [I] Persistent Cache Ratio: 0
+[12/28/2023-07:47:57] [I] Inputs:
+[12/28/2023-07:47:57] [I] === Reporting Options ===
+[12/28/2023-07:47:57] [I] Verbose: Disabled
+[12/28/2023-07:47:57] [I] Averages: 100 inferences
+[12/28/2023-07:47:57] [I] Percentiles: 90,95,99
+[12/28/2023-07:47:57] [I] Dump refittable layers:Disabled
+[12/28/2023-07:47:57] [I] Dump output: Disabled
+[12/28/2023-07:47:57] [I] Profile: Disabled
+[12/28/2023-07:47:57] [I] Export timing to JSON file: 
+[12/28/2023-07:47:57] [I] Export output to JSON file: 
+[12/28/2023-07:47:57] [I] Export profile to JSON file: 
+[12/28/2023-07:47:57] [I] 
+[12/28/2023-07:47:57] [I] === Device Information ===
+[12/28/2023-07:47:57] [I] Selected Device: Orin
+[12/28/2023-07:47:57] [I] Compute Capability: 8.7
+[12/28/2023-07:47:57] [I] SMs: 8
+[12/28/2023-07:47:57] [I] Compute Clock Rate: 0.624 GHz
+[12/28/2023-07:47:57] [I] Device Global Memory: 7471 MiB
+[12/28/2023-07:47:57] [I] Shared Memory per SM: 164 KiB
+[12/28/2023-07:47:57] [I] Memory Bus Width: 128 bits (ECC disabled)
+[12/28/2023-07:47:57] [I] Memory Clock Rate: 0.624 GHz
+[12/28/2023-07:47:57] [I] 
+[12/28/2023-07:47:57] [I] TensorRT version: 8.5.2
+[12/28/2023-07:47:58] [I] [TRT] [MemUsageChange] Init CUDA: CPU +220, GPU +0, now: CPU 249, GPU 3022 (MiB)
+[12/28/2023-07:48:00] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +302, GPU +284, now: CPU 574, GPU 3325 (MiB)
+[12/28/2023-07:48:00] [I] Start parsing network model
+[12/28/2023-07:48:01] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-07:48:01] [I] [TRT] Input filename:   yolo_nas_pose_m_fp16.onnx
+[12/28/2023-07:48:01] [I] [TRT] ONNX IR version:  0.0.8
+[12/28/2023-07:48:01] [I] [TRT] Opset version:    17
+[12/28/2023-07:48:01] [I] [TRT] Producer name:    pytorch
+[12/28/2023-07:48:01] [I] [TRT] Producer version: 2.1.2
+[12/28/2023-07:48:01] [I] [TRT] Domain:           
+[12/28/2023-07:48:01] [I] [TRT] Model version:    0
+[12/28/2023-07:48:01] [I] [TRT] Doc string:       
+[12/28/2023-07:48:01] [I] [TRT] ----------------------------------------------------------------
+[12/28/2023-07:48:01] [I] Finish parsing network model
+[12/28/2023-07:48:01] [I] [TRT] ---------- Layers Running on DLA ----------
+[12/28/2023-07:48:01] [I] [TRT] ---------- Layers Running on GPU ----------
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation1]
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/pre_process/pre_process.0/Cast.../pre_process/pre_process.2/Mul]}
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 410) [Constant]
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 411) [Constant]
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 412) [Constant]
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stem/conv/rbr_reparam/Conv + /model/backbone/stem/conv/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/downsample/rbr_reparam/Conv + /model/backbone/stage1/downsample/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv2/conv/Conv + /model/backbone/stage1/blocks/conv2/act/Relu || /model/backbone/stage1/blocks/conv1/conv/Conv + /model/backbone/stage1/blocks/conv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 15) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 23) [Shuffle] + /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage1/blocks/conv3/conv/Conv + /model/backbone/stage1/blocks/conv3/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_skip2/conv/Conv + /model/neck/neck2/reduce_skip2/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/downsample/rbr_reparam/Conv + /model/backbone/stage2/downsample/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/downsample/conv/Conv + /model/neck/neck2/downsample/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv2/conv/Conv + /model/backbone/stage2/blocks/conv2/act/Relu || /model/backbone/stage2/blocks/conv1/conv/Conv + /model/backbone/stage2/blocks/conv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 44) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 52) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 60) [Shuffle] + /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage2/blocks/conv3/conv/Conv + /model/backbone/stage2/blocks/conv3/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip2/conv/Conv + /model/neck/neck1/reduce_skip2/act/Relu || /model/neck/neck2/reduce_skip1/conv/Conv + /model/neck/neck2/reduce_skip1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/downsample/rbr_reparam/Conv + /model/backbone/stage3/downsample/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/downsample/conv/Conv + /model/neck/neck1/downsample/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv2/conv/Conv + /model/backbone/stage3/blocks/conv2/act/Relu || /model/backbone/stage3/blocks/conv1/conv/Conv + /model/backbone/stage3/blocks/conv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 83) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 91) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.2.alpha + (Unnamed Layer* 99) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.3.alpha + (Unnamed Layer* 107) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/rbr_reparam/Conv + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage3.blocks.bottlenecks.4.alpha + (Unnamed Layer* 115) [Shuffle] + /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Mul, /model/backbone/stage3/blocks/bottlenecks/bottlenecks.4/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv1/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.0/Add_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.1/Add_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.2/Add_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/bottlenecks/bottlenecks.3/Add_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage3/blocks/conv3/conv/Conv + /model/backbone/stage3/blocks/conv3/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_skip1/conv/Conv + /model/neck/neck1/reduce_skip1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/downsample/rbr_reparam/Conv + /model/backbone/stage4/downsample/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv2/conv/Conv + /model/backbone/stage4/blocks/conv2/act/Relu || /model/backbone/stage4/blocks/conv1/conv/Conv + /model/backbone/stage4/blocks/conv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 134) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.backbone.stage4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 142) [Shuffle] + /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Mul, /model/backbone/stage4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/stage4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/stage4/blocks/conv3/conv/Conv + /model/backbone/stage4/blocks/conv3/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv1/conv/Conv + /model/backbone/context_module/cv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.2/MaxPool
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.1/MaxPool
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POOLING: /model/backbone/context_module/m.0/MaxPool
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/backbone/context_module/cv1/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/backbone/context_module/cv2/conv/Conv + /model/backbone/context_module/cv2/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/conv/conv/Conv + /model/neck/neck1/conv/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck1/upsample/ConvTranspose
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/reduce_after_concat/conv/Conv + /model/neck/neck1/reduce_after_concat/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv2/conv/Conv + /model/neck/neck1/blocks/conv2/act/Relu || /model/neck/neck1/blocks/conv1/conv/Conv + /model/neck/neck1/blocks/conv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.0.alpha + (Unnamed Layer* 171) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck1.blocks.bottlenecks.1.alpha + (Unnamed Layer* 179) [Shuffle] + /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck1/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/neck/neck1/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck1/blocks/conv3/conv/Conv + /model/neck/neck1/blocks/conv3/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/conv/conv/Conv + /model/neck/neck2/conv/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] DECONVOLUTION: /model/neck/neck2/upsample/ConvTranspose
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/reduce_skip1/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/reduce_after_concat/conv/Conv + /model/neck/neck2/reduce_after_concat/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv2/conv/Conv + /model/neck/neck2/blocks/conv2/act/Relu || /model/neck/neck2/blocks/conv1/conv/Conv + /model/neck/neck2/blocks/conv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.0.alpha + (Unnamed Layer* 200) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.1.alpha + (Unnamed Layer* 208) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv1/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/rbr_reparam/Conv + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/cv2/nonlinearity/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck2.blocks.bottlenecks.2.alpha + (Unnamed Layer* 216) [Shuffle] + /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck2/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/neck/neck2/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck2/blocks/conv3/conv/Conv + /model/neck/neck2/blocks/conv3/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/bbox_stem/seq/conv/Conv + /model/heads/head1/bbox_stem/seq/act/Relu || /model/heads/head1/pose_stem/seq/conv/Conv + /model/heads/head1/pose_stem/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/conv/conv/Conv + /model/neck/neck3/conv/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head1/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head1/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head1/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv2/conv/Conv + /model/neck/neck3/blocks/conv2/act/Relu || /model/neck/neck3/blocks/conv1/conv/Conv + /model/neck/neck3/blocks/conv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/cls_pred/Conv
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/reg_pred/Conv
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head1/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape + /model/heads/Transpose
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head1/pose_pred/Conv
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.0.alpha + (Unnamed Layer* 247) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck3.blocks.bottlenecks.1.alpha + (Unnamed Layer* 270) [Shuffle] + /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck3/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/neck/neck3/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck3/blocks/conv3/conv/Conv + /model/neck/neck3/blocks/conv3/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_stem/seq/conv/Conv + /model/heads/head2/pose_stem/seq/act/Relu || /model/heads/head2/bbox_stem/seq/conv/Conv + /model/heads/head2/bbox_stem/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/conv/conv/Conv + /model/neck/neck4/conv/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head2/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head2/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head2/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv2/conv/Conv + /model/neck/neck4/blocks/conv2/act/Relu || /model/neck/neck4/blocks/conv1/conv/Conv + /model/neck/neck4/blocks/conv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/cls_pred/Conv
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/reg_pred/Conv
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head2/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_4 + /model/heads/Transpose_3
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head2/pose_pred/Conv
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/cv2/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_1
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.0.alpha + (Unnamed Layer* 301) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.0/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_1
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/cv2/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.1.alpha + (Unnamed Layer* 324) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.1/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv1/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/conv/Conv + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/cv2/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] POINTWISE: PWN(model.neck.neck4.blocks.bottlenecks.2.alpha + (Unnamed Layer* 332) [Shuffle] + /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Mul, /model/neck/neck4/blocks/bottlenecks/bottlenecks.2/Add)
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] COPY: /model/neck/neck4/blocks/conv2/act/Relu_output_0 copy
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/neck/neck4/blocks/conv3/conv/Conv + /model/neck/neck4/blocks/conv3/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/bbox_stem/seq/conv/Conv + /model/heads/head3/bbox_stem/seq/act/Relu || /model/heads/head3/pose_stem/seq/conv/Conv + /model/heads/head3/pose_stem/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_convs/reg_convs.0/seq/conv/Conv + /model/heads/head3/reg_convs/reg_convs.0/seq/act/Relu || /model/heads/head3/cls_convs/cls_convs.0/seq/conv/Conv + /model/heads/head3/cls_convs/cls_convs.0/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.0/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.0/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/cls_pred/Conv
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/reg_pred/Conv
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.1/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.1/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] SHUFFLE: /model/heads/Reshape_8 + /model/heads/Transpose_6
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_convs/pose_convs.2/seq/conv/Conv + /model/heads/head3/pose_convs/pose_convs.2/seq/act/Relu
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] SOFTMAX: /model/heads/Softmax_2
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/head3/pose_pred/Conv
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] CONVOLUTION: /model/heads/Conv_2
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice_1...cast_boxes_to_fp32]}
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] NMS: batched_nms_26
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] DEVICE_TO_SHAPE_HOST: (Unnamed Layer* 414) [NMS]_1_output[DevicetoShapeHostCopy]
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation2]
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[/model/heads/head1/Slice...graph2_/Concat_5]}
+[12/28/2023-07:48:01] [I] [TRT] [GpuLayer] TRAIN_STATION: [trainStation3]
+[12/28/2023-07:48:12] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +534, GPU +430, now: CPU 1195, GPU 3835 (MiB)
+[12/28/2023-07:48:14] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +83, GPU +64, now: CPU 1278, GPU 3899 (MiB)
+[12/28/2023-07:48:14] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
+[12/28/2023-08:44:43] [I] [TRT] Total Activation Memory: 8017417728
+[12/28/2023-08:44:44] [I] [TRT] Detected 1 inputs and 1 output network tensors.
+[12/28/2023-08:44:54] [I] [TRT] Total Host Persistent Memory: 330944
+[12/28/2023-08:44:54] [I] [TRT] Total Device Persistent Memory: 115712
+[12/28/2023-08:44:54] [I] [TRT] Total Scratch Memory: 134217728
+[12/28/2023-08:44:54] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 40 MiB, GPU 2398 MiB
+[12/28/2023-08:44:54] [I] [TRT] [BlockAssignment] Started assigning block shifts. This will take 181 steps to complete.
+[12/28/2023-08:44:54] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 85.1996ms to assign 14 blocks to 181 nodes requiring 155574784 bytes.
+[12/28/2023-08:44:54] [I] [TRT] Total Activation Memory: 155574784
+[12/28/2023-08:44:59] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1625, GPU 5501 (MiB)
+[12/28/2023-08:44:59] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +10, GPU +128, now: CPU 10, GPU 128 (MiB)
+[12/28/2023-08:45:00] [I] Engine built in 3422.28 sec.
+[12/28/2023-08:45:00] [I] [TRT] Loaded engine size: 76 MiB
+[12/28/2023-08:45:00] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1317, GPU 5134 (MiB)
+[12/28/2023-08:45:00] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +74, now: CPU 0, GPU 74 (MiB)
+[12/28/2023-08:45:00] [I] Engine deserialized in 0.264761 sec.
+[12/28/2023-08:45:00] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1317, GPU 5134 (MiB)
+[12/28/2023-08:45:01] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +148, now: CPU 0, GPU 222 (MiB)
+[12/28/2023-08:45:01] [I] Setting persistentCacheLimit to 0 bytes.
+[12/28/2023-08:45:01] [I] Using random values for input onnx::Cast_0
+[12/28/2023-08:45:01] [I] Created input binding for onnx::Cast_0 with dimensions 1x3x640x640
+[12/28/2023-08:45:01] [I] Using random values for output graph2_flat_predictions
+[12/28/2023-08:45:01] [I] Created output binding for graph2_flat_predictions with dimensions -1x57
+[12/28/2023-08:45:01] [I] Starting inference
+[12/28/2023-08:45:16] [I] Warmup completed 2 queries over 200 ms
+[12/28/2023-08:45:16] [I] Timing trace has 569 queries over 15.0311 s
+[12/28/2023-08:45:16] [I] 
+[12/28/2023-08:45:16] [I] === Trace details ===
+[12/28/2023-08:45:16] [I] Trace averages of 100 runs:
+[12/28/2023-08:45:16] [I] Average on 100 runs - GPU latency: 26.4061 ms - Host latency: 26.5181 ms (enqueue 26.4696 ms)
+[12/28/2023-08:45:16] [I] Average on 100 runs - GPU latency: 26.2062 ms - Host latency: 26.3239 ms (enqueue 26.2673 ms)
+[12/28/2023-08:45:16] [I] Average on 100 runs - GPU latency: 26.2202 ms - Host latency: 26.3345 ms (enqueue 26.2829 ms)
+[12/28/2023-08:45:16] [I] Average on 100 runs - GPU latency: 26.1667 ms - Host latency: 26.2764 ms (enqueue 26.2337 ms)
+[12/28/2023-08:45:16] [I] Average on 100 runs - GPU latency: 26.4629 ms - Host latency: 26.5727 ms (enqueue 26.5274 ms)
+[12/28/2023-08:45:16] [I] 
+[12/28/2023-08:45:16] [I] === Performance summary ===
+[12/28/2023-08:45:16] [I] Throughput: 37.8547 qps
+[12/28/2023-08:45:16] [I] Latency: min = 25.1152 ms, max = 32.1547 ms, mean = 26.393 ms, median = 26.3442 ms, percentile(90%) = 27.0601 ms, percentile(95%) = 27.4189 ms, percentile(99%) = 29.4863 ms
+[12/28/2023-08:45:16] [I] Enqueue Time: min = 25.0762 ms, max = 32.1133 ms, mean = 26.3436 ms, median = 26.2896 ms, percentile(90%) = 26.9199 ms, percentile(95%) = 27.0813 ms, percentile(99%) = 29.4521 ms
+[12/28/2023-08:45:16] [I] H2D Latency: min = 0.0800781 ms, max = 0.117188 ms, mean = 0.0960489 ms, median = 0.097168 ms, percentile(90%) = 0.0996094 ms, percentile(95%) = 0.100098 ms, percentile(99%) = 0.101318 ms
+[12/28/2023-08:45:16] [I] GPU Compute Time: min = 25.0037 ms, max = 32.0377 ms, mean = 26.281 ms, median = 26.2241 ms, percentile(90%) = 26.9429 ms, percentile(95%) = 27.3164 ms, percentile(99%) = 29.3721 ms
+[12/28/2023-08:45:16] [I] D2H Latency: min = 0.00292969 ms, max = 0.0490723 ms, mean = 0.0159815 ms, median = 0.0146484 ms, percentile(90%) = 0.0253906 ms, percentile(95%) = 0.0271912 ms, percentile(99%) = 0.0324707 ms
+[12/28/2023-08:45:16] [I] Total Host Walltime: 15.0311 s
+[12/28/2023-08:45:16] [I] Total GPU Compute Time: 14.9539 s
+[12/28/2023-08:45:16] [I] Explanations of the performance metrics are printed in the verbose logs.
+[12/28/2023-08:45:16] [I] 
+&&&& PASSED TensorRT.trtexec [TensorRT v8502] # /usr/src/tensorrt/bin/trtexec --onnx=yolo_nas_pose_m_fp16.onnx --fp16 --avgRuns=100 --duration=15 --saveEngine=yolo_nas_pose_m_fp16.onnx.fp16.engine

yolo_nas_pose_m_fp16.onnx.int8.engine.err

@@ -0,0 +1,8 @@
+[12/28/2023-10:38:24] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
+[12/28/2023-10:38:24] [W] [TRT] onnx2trt_utils.cpp:403: One or more weights outside the range of INT32 was clamped
+[12/28/2023-10:38:24] [E] Error[4]: [network.cpp::validate::2925] Error Code 4: Internal Error (fp16 precision has been set for a layer or layer output, but fp16 is not configured in the builder)
+[12/28/2023-10:38:24] [E] Error[2]: [builder.cpp::buildSerializedNetwork::751] Error Code 2: Internal Error (Assertion engine != nullptr failed. )
+[12/28/2023-10:38:24] [E] Engine could not be created from network
+[12/28/2023-10:38:24] [E] Building engine failed
+[12/28/2023-10:38:24] [E] Failed to create engine from model or file.
+[12/28/2023-10:38:24] [E] Engine set up failed