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 |
|
38 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library |
|
39 |
|
40 |
|
41 |
## Installation
|
@@ -96,16 +96,16 @@ python -m qai_hub_models.models.ffnet_54s.export
|
|
96 |
```
|
97 |
Profile Job summary of FFNet-54S
|
98 |
--------------------------------------------------
|
99 |
-
Device: Samsung Galaxy
|
100 |
-
Estimated Inference Time:
|
101 |
-
Estimated Peak Memory Range:
|
102 |
Compute Units: NPU (113) | Total (113)
|
103 |
|
104 |
Profile Job summary of FFNet-54S
|
105 |
--------------------------------------------------
|
106 |
-
Device: Samsung Galaxy
|
107 |
-
Estimated Inference Time:
|
108 |
-
Estimated Peak Memory Range:
|
109 |
Compute Units: NPU (176) | Total (176)
|
110 |
|
111 |
|
@@ -211,7 +211,7 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
|
|
211 |
## License
|
212 |
- The license for the original implementation of FFNet-54S can be found
|
213 |
[here](https://github.com/Qualcomm-AI-research/FFNet/blob/master/LICENSE).
|
214 |
-
- The license for the compiled assets for on-device deployment can be found [here](
|
215 |
|
216 |
## References
|
217 |
* [Simple and Efficient Architectures for Semantic Segmentation](https://arxiv.org/abs/2206.08236)
|
|
|
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 | 24.853 ms | 2 - 5 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite)
|
38 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 19.975 ms | 24 - 50 MB | FP16 | NPU | [FFNet-54S.so](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.so)
|
39 |
|
40 |
|
41 |
## Installation
|
|
|
96 |
```
|
97 |
Profile Job summary of FFNet-54S
|
98 |
--------------------------------------------------
|
99 |
+
Device: Samsung Galaxy S24 (14)
|
100 |
+
Estimated Inference Time: 18.42 ms
|
101 |
+
Estimated Peak Memory Range: 0.44-107.92 MB
|
102 |
Compute Units: NPU (113) | Total (113)
|
103 |
|
104 |
Profile Job summary of FFNet-54S
|
105 |
--------------------------------------------------
|
106 |
+
Device: Samsung Galaxy S24 (14)
|
107 |
+
Estimated Inference Time: 14.57 ms
|
108 |
+
Estimated Peak Memory Range: 146.99-207.62 MB
|
109 |
Compute Units: NPU (176) | Total (176)
|
110 |
|
111 |
|
|
|
211 |
## License
|
212 |
- The license for the original implementation of FFNet-54S can be found
|
213 |
[here](https://github.com/Qualcomm-AI-research/FFNet/blob/master/LICENSE).
|
214 |
+
- The license for the compiled assets for on-device deployment can be found [here]({deploy_license_url})
|
215 |
|
216 |
## References
|
217 |
* [Simple and Efficient Architectures for Semantic Segmentation](https://arxiv.org/abs/2206.08236)
|