Upload README.md with huggingface_hub

README.md

@@ -18,7 +18,7 @@ tags:
 
 WideResNet50 is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
 
-This model is an implementation of WideResNet50 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py).
+This model is an implementation of WideResNet50 found [here]({source_repo}).
 This repository provides scripts to run WideResNet50 on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/wideresnet50).
@@ -33,15 +33,32 @@ More details on model performance across various devices, can be found
   - Number of parameters: 68.8M
   - Model size: 263 MB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| WideResNet50 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 4.887 ms | 0 - 2 MB | FP16 | NPU | [WideResNet50.tflite](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.tflite) |
+| WideResNet50 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 5.677 ms | 1 - 346 MB | FP16 | NPU | [WideResNet50.so](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.so) |
+| WideResNet50 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 5.217 ms | 1 - 2 MB | FP16 | NPU | [WideResNet50.onnx](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.onnx) |
+| WideResNet50 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 3.989 ms | 0 - 101 MB | FP16 | NPU | [WideResNet50.tflite](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.tflite) |
+| WideResNet50 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 4.603 ms | 1 - 27 MB | FP16 | NPU | [WideResNet50.so](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.so) |
+| WideResNet50 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 4.293 ms | 0 - 106 MB | FP16 | NPU | [WideResNet50.onnx](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.onnx) |
+| WideResNet50 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 4.847 ms | 0 - 2 MB | FP16 | NPU | [WideResNet50.tflite](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.tflite) |
+| WideResNet50 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 5.026 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| WideResNet50 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 4.872 ms | 0 - 2 MB | FP16 | NPU | [WideResNet50.tflite](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.tflite) |
+| WideResNet50 | SA8255 (Proxy) | SA8255P Proxy | QNN | 5.033 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| WideResNet50 | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 4.86 ms | 0 - 2 MB | FP16 | NPU | [WideResNet50.tflite](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.tflite) |
+| WideResNet50 | SA8775 (Proxy) | SA8775P Proxy | QNN | 5.031 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| WideResNet50 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 4.878 ms | 0 - 1 MB | FP16 | NPU | [WideResNet50.tflite](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.tflite) |
+| WideResNet50 | SA8650 (Proxy) | SA8650P Proxy | QNN | 5.029 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| WideResNet50 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 7.138 ms | 0 - 90 MB | FP16 | NPU | [WideResNet50.tflite](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.tflite) |
+| WideResNet50 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 7.222 ms | 1 - 25 MB | FP16 | NPU | Use Export Script |
+| WideResNet50 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 3.063 ms | 0 - 32 MB | FP16 | NPU | [WideResNet50.tflite](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.tflite) |
+| WideResNet50 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 4.069 ms | 0 - 26 MB | FP16 | NPU | Use Export Script |
+| WideResNet50 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 3.52 ms | 0 - 37 MB | FP16 | NPU | [WideResNet50.onnx](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.onnx) |
+| WideResNet50 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.938 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
+| WideResNet50 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 4.711 ms | 133 - 133 MB | FP16 | NPU | [WideResNet50.onnx](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.onnx) |
 
 
 
-| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
-| ---|---|---|---|---|---|---|---|
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 4.868 ms | 0 - 2 MB | FP16 | NPU |  [WideResNet50.tflite](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 5.71 ms | 1 - 207 MB | FP16 | NPU |  [WideResNet50.so](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.so) 
-
-
 
 ## Installation
 
@@ -96,16 +113,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.wideresnet50.export
 ```
-
 ```
-Profile Job summary of WideResNet50
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 4.70 ms
-Estimated Peak Memory Range: 0.57-0.57 MB
-Compute Units: NPU (126) | Total (126)
-
-
+Profiling Results
+------------------------------------------------------------
+WideResNet50
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE                 
+Estimated inference time (ms)   : 4.9                    
+Estimated peak memory usage (MB): [0, 2]                 
+Total # Ops                     : 79                     
+Compute Unit(s)                 : NPU (79 ops)           
 ```
 
 
@@ -204,15 +221,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on WideResNet50's performance across various devices [here](https://aihub.qualcomm.com/models/wideresnet50).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of WideResNet50 can be found
-  [here](https://github.com/pytorch/vision/blob/main/LICENSE).
-- 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)
+* The license for the original implementation of WideResNet50 can be found [here](https://github.com/pytorch/vision/blob/main/LICENSE).
+* 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)
+
+
 
 ## References
 * [Wide Residual Networks](https://arxiv.org/abs/1605.07146)
 * [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py)
 
+
+
 ## Community
 * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
 * For questions or feedback please [reach out to us](mailto:[email protected]).