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 | 22.
|
39 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 17.
|
40 |
|
41 |
|
42 |
## Installation
|
@@ -97,16 +97,16 @@ python -m qai_hub_models.models.ffnet_40s.export
|
|
97 |
```
|
98 |
Profile Job summary of FFNet-40S
|
99 |
--------------------------------------------------
|
100 |
-
Device: Samsung Galaxy
|
101 |
-
Estimated Inference Time:
|
102 |
-
Estimated Peak Memory Range:
|
103 |
Compute Units: NPU (92) | Total (92)
|
104 |
|
105 |
Profile Job summary of FFNet-40S
|
106 |
--------------------------------------------------
|
107 |
-
Device: Samsung Galaxy
|
108 |
-
Estimated Inference Time:
|
109 |
-
Estimated Peak Memory Range: 24.
|
110 |
Compute Units: NPU (141) | Total (141)
|
111 |
|
112 |
|
@@ -212,7 +212,7 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
|
|
212 |
## License
|
213 |
- The license for the original implementation of FFNet-40S can be found
|
214 |
[here](https://github.com/Qualcomm-AI-research/FFNet/blob/master/LICENSE).
|
215 |
-
- The license for the compiled assets for on-device deployment can be found [here](
|
216 |
|
217 |
## References
|
218 |
* [Simple and Efficient Architectures for Semantic Segmentation](https://arxiv.org/abs/2206.08236)
|
|
|
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 | 22.513 ms | 2 - 5 MB | FP16 | NPU | [FFNet-40S.tflite](https://huggingface.co/qualcomm/FFNet-40S/blob/main/FFNet-40S.tflite)
|
39 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 17.466 ms | 24 - 46 MB | FP16 | NPU | [FFNet-40S.so](https://huggingface.co/qualcomm/FFNet-40S/blob/main/FFNet-40S.so)
|
40 |
|
41 |
|
42 |
## Installation
|
|
|
97 |
```
|
98 |
Profile Job summary of FFNet-40S
|
99 |
--------------------------------------------------
|
100 |
+
Device: Samsung Galaxy S24 (14)
|
101 |
+
Estimated Inference Time: 16.61 ms
|
102 |
+
Estimated Peak Memory Range: 0.06-95.83 MB
|
103 |
Compute Units: NPU (92) | Total (92)
|
104 |
|
105 |
Profile Job summary of FFNet-40S
|
106 |
--------------------------------------------------
|
107 |
+
Device: Samsung Galaxy S24 (14)
|
108 |
+
Estimated Inference Time: 12.68 ms
|
109 |
+
Estimated Peak Memory Range: 24.02-78.73 MB
|
110 |
Compute Units: NPU (141) | Total (141)
|
111 |
|
112 |
|
|
|
212 |
## License
|
213 |
- The license for the original implementation of FFNet-40S can be found
|
214 |
[here](https://github.com/Qualcomm-AI-research/FFNet/blob/master/LICENSE).
|
215 |
+
- The license for the compiled assets for on-device deployment can be found [here]({deploy_license_url})
|
216 |
|
217 |
## References
|
218 |
* [Simple and Efficient Architectures for Semantic Segmentation](https://arxiv.org/abs/2206.08236)
|