Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -35,8 +35,8 @@ More details on model performance across various devices, can be found
|
|
35 |
|
36 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
37 |
| ---|---|---|---|---|---|---|---|
|
38 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.
|
39 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.
|
40 |
|
41 |
|
42 |
## Installation
|
@@ -96,17 +96,17 @@ python -m qai_hub_models.models.googlenet.export
|
|
96 |
```
|
97 |
Profile Job summary of GoogLeNet
|
98 |
--------------------------------------------------
|
99 |
-
Device: Samsung Galaxy
|
100 |
-
Estimated Inference Time:
|
101 |
-
Estimated Peak Memory Range: 0.02-
|
102 |
-
Compute Units: NPU (
|
103 |
|
104 |
Profile Job summary of GoogLeNet
|
105 |
--------------------------------------------------
|
106 |
-
Device: Samsung Galaxy
|
107 |
-
Estimated Inference Time:
|
108 |
-
Estimated Peak Memory Range: 0.
|
109 |
-
Compute Units: NPU (
|
110 |
|
111 |
|
112 |
```
|
@@ -225,7 +225,7 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
|
|
225 |
## License
|
226 |
- The license for the original implementation of GoogLeNet can be found
|
227 |
[here](https://github.com/pytorch/vision/blob/main/LICENSE).
|
228 |
-
- The license for the compiled assets for on-device deployment can be found [here](
|
229 |
|
230 |
## References
|
231 |
* [Going Deeper with Convolutions](https://arxiv.org/abs/1409.4842)
|
|
|
35 |
|
36 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
37 |
| ---|---|---|---|---|---|---|---|
|
38 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.041 ms | 0 - 2 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite)
|
39 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.083 ms | 0 - 25 MB | FP16 | NPU | [GoogLeNet.so](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.so)
|
40 |
|
41 |
|
42 |
## Installation
|
|
|
96 |
```
|
97 |
Profile Job summary of GoogLeNet
|
98 |
--------------------------------------------------
|
99 |
+
Device: Samsung Galaxy S24 (14)
|
100 |
+
Estimated Inference Time: 0.65 ms
|
101 |
+
Estimated Peak Memory Range: 0.02-43.31 MB
|
102 |
+
Compute Units: NPU (84) | Total (84)
|
103 |
|
104 |
Profile Job summary of GoogLeNet
|
105 |
--------------------------------------------------
|
106 |
+
Device: Samsung Galaxy S24 (14)
|
107 |
+
Estimated Inference Time: 0.68 ms
|
108 |
+
Estimated Peak Memory Range: 0.00-47.66 MB
|
109 |
+
Compute Units: NPU (144) | Total (144)
|
110 |
|
111 |
|
112 |
```
|
|
|
225 |
## License
|
226 |
- The license for the original implementation of GoogLeNet can be found
|
227 |
[here](https://github.com/pytorch/vision/blob/main/LICENSE).
|
228 |
+
- The license for the compiled assets for on-device deployment can be found [here]({deploy_license_url})
|
229 |
|
230 |
## References
|
231 |
* [Going Deeper with Convolutions](https://arxiv.org/abs/1409.4842)
|