Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -38,8 +38,8 @@ More details on model performance across various devices, can be found
|
|
| 38 |
|
| 39 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 40 |
| ---|---|---|---|---|---|---|---|
|
| 41 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 2.
|
| 42 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.
|
| 43 |
|
| 44 |
|
| 45 |
|
|
@@ -101,8 +101,8 @@ python -m qai_hub_models.models.resnext50.export
|
|
| 101 |
Profile Job summary of ResNeXt50
|
| 102 |
--------------------------------------------------
|
| 103 |
Device: SA8255 (Proxy) (13)
|
| 104 |
-
Estimated Inference Time: 2.
|
| 105 |
-
Estimated Peak Memory Range: 0.
|
| 106 |
Compute Units: NPU (126) | Total (126)
|
| 107 |
|
| 108 |
|
|
|
|
| 38 |
|
| 39 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 40 |
| ---|---|---|---|---|---|---|---|
|
| 41 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 2.51 ms | 0 - 1 MB | FP16 | NPU | [ResNeXt50.tflite](https://huggingface.co/qualcomm/ResNeXt50/blob/main/ResNeXt50.tflite)
|
| 42 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.591 ms | 0 - 84 MB | FP16 | NPU | [ResNeXt50.so](https://huggingface.co/qualcomm/ResNeXt50/blob/main/ResNeXt50.so)
|
| 43 |
|
| 44 |
|
| 45 |
|
|
|
|
| 101 |
Profile Job summary of ResNeXt50
|
| 102 |
--------------------------------------------------
|
| 103 |
Device: SA8255 (Proxy) (13)
|
| 104 |
+
Estimated Inference Time: 2.56 ms
|
| 105 |
+
Estimated Peak Memory Range: 0.03-93.60 MB
|
| 106 |
Compute Units: NPU (126) | Total (126)
|
| 107 |
|
| 108 |
|