Specify task as "object detection"
Browse files
README.md
CHANGED
|
@@ -1,3 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
We offer a TensorRT model in various precisions including int8, fp16, fp32, and mixed, converted from Deci-AI's YOLO-NAS-Pose pre-trained weights in PyTorch. This model is compatible with Jetson Orin Nano hardware.
|
| 2 |
|
| 3 |
# Large
|
|
@@ -53,4 +56,4 @@ We offer a TensorRT model in various precisions including int8, fp16, fp32, and
|
|
| 53 |
| yolo_nas_pose_s_int8.onnx.best.engine | INT8 | FP32+FP16+INT8 | 80.8271 qps |
|
| 54 |
| yolo_nas_pose_s_int8.onnx.int8.engine | INT8 | FP32+INT8 | 74.2658 qps |
|
| 55 |
|
| 56 |
-
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: object-detection
|
| 3 |
+
---
|
| 4 |
We offer a TensorRT model in various precisions including int8, fp16, fp32, and mixed, converted from Deci-AI's YOLO-NAS-Pose pre-trained weights in PyTorch. This model is compatible with Jetson Orin Nano hardware.
|
| 5 |
|
| 6 |
# Large
|
|
|
|
| 56 |
| yolo_nas_pose_s_int8.onnx.best.engine | INT8 | FP32+FP16+INT8 | 80.8271 qps |
|
| 57 |
| yolo_nas_pose_s_int8.onnx.int8.engine | INT8 | FP32+INT8 | 74.2658 qps |
|
| 58 |
|
| 59 |
+
|