qaihm-bot commited on
Commit
5f78ab6
·
verified ·
1 Parent(s): 327e683

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +9 -9
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 | 3.008 ms | 0 - 1 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite)
40
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.895 ms | 1 - 216 MB | FP16 | NPU | [ResNet101.so](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.so)
41
 
42
 
43
  ## Installation
@@ -97,16 +97,16 @@ python -m qai_hub_models.models.resnet101.export
97
  ```
98
  Profile Job summary of ResNet101
99
  --------------------------------------------------
100
- Device: Samsung Galaxy S23 Ultra (13)
101
- Estimated Inference Time: 3.01 ms
102
- Estimated Peak Memory Range: 0.03-1.44 MB
103
  Compute Units: NPU (145) | Total (145)
104
 
105
  Profile Job summary of ResNet101
106
  --------------------------------------------------
107
- Device: Samsung Galaxy S23 Ultra (13)
108
- Estimated Inference Time: 2.90 ms
109
- Estimated Peak Memory Range: 0.59-216.11 MB
110
  Compute Units: NPU (244) | Total (244)
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 ResNet101 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](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf).
230
 
231
  ## References
232
  * [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)
 
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 | 2.993 ms | 0 - 2 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite)
40
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.921 ms | 1 - 216 MB | FP16 | NPU | [ResNet101.so](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.so)
41
 
42
 
43
  ## Installation
 
97
  ```
98
  Profile Job summary of ResNet101
99
  --------------------------------------------------
100
+ Device: Samsung Galaxy S24 (14)
101
+ Estimated Inference Time: 2.22 ms
102
+ Estimated Peak Memory Range: 0.02-98.23 MB
103
  Compute Units: NPU (145) | Total (145)
104
 
105
  Profile Job summary of ResNet101
106
  --------------------------------------------------
107
+ Device: Samsung Galaxy S24 (14)
108
+ Estimated Inference Time: 2.13 ms
109
+ Estimated Peak Memory Range: 0.59-68.45 MB
110
  Compute Units: NPU (244) | Total (244)
111
 
112
 
 
226
  ## License
227
  - The license for the original implementation of ResNet101 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
  * [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)