Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -34,8 +34,8 @@ More details on model performance across various devices, can be found
|
|
34 |
|
35 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
36 |
| ---|---|---|---|---|---|---|---|
|
37 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 3.
|
38 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 3.
|
39 |
|
40 |
|
41 |
|
@@ -98,7 +98,7 @@ python -m qai_hub_models.models.midas.export
|
|
98 |
Profile Job summary of Midas-V2
|
99 |
--------------------------------------------------
|
100 |
Device: Snapdragon X Elite CRD (11)
|
101 |
-
Estimated Inference Time: 3.
|
102 |
Estimated Peak Memory Range: 0.75-0.75 MB
|
103 |
Compute Units: NPU (199) | Total (199)
|
104 |
|
@@ -125,7 +125,6 @@ from qai_hub_models.models.midas import Model
|
|
125 |
|
126 |
# Load the model
|
127 |
torch_model = Model.from_pretrained()
|
128 |
-
torch_model.eval()
|
129 |
|
130 |
# Device
|
131 |
device = hub.Device("Samsung Galaxy S23")
|
|
|
34 |
|
35 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
36 |
| ---|---|---|---|---|---|---|---|
|
37 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 3.432 ms | 0 - 2 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite)
|
38 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 3.375 ms | 1 - 11 MB | FP16 | NPU | [Midas-V2.so](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.so)
|
39 |
|
40 |
|
41 |
|
|
|
98 |
Profile Job summary of Midas-V2
|
99 |
--------------------------------------------------
|
100 |
Device: Snapdragon X Elite CRD (11)
|
101 |
+
Estimated Inference Time: 3.37 ms
|
102 |
Estimated Peak Memory Range: 0.75-0.75 MB
|
103 |
Compute Units: NPU (199) | Total (199)
|
104 |
|
|
|
125 |
|
126 |
# Load the model
|
127 |
torch_model = Model.from_pretrained()
|
|
|
128 |
|
129 |
# Device
|
130 |
device = hub.Device("Samsung Galaxy S23")
|