Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -36,8 +36,8 @@ More details on model performance across various devices, can be found
|
|
36 |
|
37 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
38 |
| ---|---|---|---|---|---|---|---|
|
39 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 2.
|
40 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.
|
41 |
|
42 |
|
43 |
## Installation
|
@@ -97,16 +97,16 @@ python -m qai_hub_models.models.efficientnet_b0.export
|
|
97 |
```
|
98 |
Profile Job summary of EfficientNet-B0
|
99 |
--------------------------------------------------
|
100 |
-
Device: Samsung Galaxy
|
101 |
-
Estimated Inference Time:
|
102 |
-
Estimated Peak Memory Range: 0.01-
|
103 |
Compute Units: NPU (243) | Total (243)
|
104 |
|
105 |
Profile Job summary of EfficientNet-B0
|
106 |
--------------------------------------------------
|
107 |
-
Device: Samsung Galaxy
|
108 |
-
Estimated Inference Time:
|
109 |
-
Estimated Peak Memory Range: 0.
|
110 |
Compute Units: NPU (242) | Total (242)
|
111 |
|
112 |
|
@@ -226,7 +226,7 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
|
|
226 |
## License
|
227 |
- The license for the original implementation of EfficientNet-B0 can be found
|
228 |
[here](https://github.com/pytorch/vision/blob/main/LICENSE).
|
229 |
-
- The license for the compiled assets for on-device deployment can be found [here](
|
230 |
|
231 |
## References
|
232 |
* [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946)
|
|
|
36 |
|
37 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
38 |
| ---|---|---|---|---|---|---|---|
|
39 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 2.174 ms | 0 - 2 MB | FP16 | NPU | [EfficientNet-B0.tflite](https://huggingface.co/qualcomm/EfficientNet-B0/blob/main/EfficientNet-B0.tflite)
|
40 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.173 ms | 0 - 83 MB | FP16 | NPU | [EfficientNet-B0.so](https://huggingface.co/qualcomm/EfficientNet-B0/blob/main/EfficientNet-B0.so)
|
41 |
|
42 |
|
43 |
## Installation
|
|
|
97 |
```
|
98 |
Profile Job summary of EfficientNet-B0
|
99 |
--------------------------------------------------
|
100 |
+
Device: Samsung Galaxy S24 (14)
|
101 |
+
Estimated Inference Time: 1.52 ms
|
102 |
+
Estimated Peak Memory Range: 0.01-67.59 MB
|
103 |
Compute Units: NPU (243) | Total (243)
|
104 |
|
105 |
Profile Job summary of EfficientNet-B0
|
106 |
--------------------------------------------------
|
107 |
+
Device: Samsung Galaxy S24 (14)
|
108 |
+
Estimated Inference Time: 1.51 ms
|
109 |
+
Estimated Peak Memory Range: 0.59-75.56 MB
|
110 |
Compute Units: NPU (242) | Total (242)
|
111 |
|
112 |
|
|
|
226 |
## License
|
227 |
- The license for the original implementation of EfficientNet-B0 can be found
|
228 |
[here](https://github.com/pytorch/vision/blob/main/LICENSE).
|
229 |
+
- The license for the compiled assets for on-device deployment can be found [here]({deploy_license_url})
|
230 |
|
231 |
## References
|
232 |
* [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946)
|