Upload README.md with huggingface_hub

README.md

@@ -18,7 +18,7 @@ tags:
 
 ResNet101 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 ResNet101 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py).
+This model is an implementation of ResNet101 found [here]({source_repo}).
 This repository provides scripts to run ResNet101 on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/resnet101).
@@ -33,15 +33,32 @@ More details on model performance across various devices, can be found
   - Number of parameters: 44.5M
   - Model size: 170 MB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| ResNet101 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 3.46 ms | 0 - 2 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
+| ResNet101 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 3.504 ms | 0 - 149 MB | FP16 | NPU | [ResNet101.so](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.so) |
+| ResNet101 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 3.631 ms | 1 - 2 MB | FP16 | NPU | [ResNet101.onnx](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.onnx) |
+| ResNet101 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.926 ms | 0 - 114 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
+| ResNet101 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.734 ms | 1 - 34 MB | FP16 | NPU | [ResNet101.so](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.so) |
+| ResNet101 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 3.791 ms | 0 - 118 MB | FP16 | NPU | [ResNet101.onnx](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.onnx) |
+| ResNet101 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 3.371 ms | 0 - 2 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
+| ResNet101 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 3.275 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| ResNet101 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 3.407 ms | 0 - 2 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
+| ResNet101 | SA8255 (Proxy) | SA8255P Proxy | QNN | 3.283 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| ResNet101 | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 3.391 ms | 0 - 6 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
+| ResNet101 | SA8775 (Proxy) | SA8775P Proxy | QNN | 3.321 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| ResNet101 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 3.422 ms | 0 - 5 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
+| ResNet101 | SA8650 (Proxy) | SA8650P Proxy | QNN | 3.286 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| ResNet101 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 4.81 ms | 0 - 92 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
+| ResNet101 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 4.825 ms | 1 - 22 MB | FP16 | NPU | Use Export Script |
+| ResNet101 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.377 ms | 0 - 43 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
+| ResNet101 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 2.401 ms | 1 - 33 MB | FP16 | NPU | Use Export Script |
+| ResNet101 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 2.51 ms | 0 - 46 MB | FP16 | NPU | [ResNet101.onnx](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.onnx) |
+| ResNet101 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.453 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
+| ResNet101 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.58 ms | 86 - 86 MB | FP16 | NPU | [ResNet101.onnx](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.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 | 3.458 ms | 0 - 2 MB | FP16 | NPU |  [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 3.505 ms | 1 - 153 MB | FP16 | NPU |  [ResNet101.so](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.so) 
-
-
 
 ## Installation
 
@@ -96,16 +113,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.resnet101.export
 ```
-
 ```
-Profile Job summary of ResNet101
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 3.48 ms
-Estimated Peak Memory Range: 0.57-0.57 MB
-Compute Units: NPU (245) | Total (245)
-
-
+Profiling Results
+------------------------------------------------------------
+ResNet101
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE                 
+Estimated inference time (ms)   : 3.5                    
+Estimated peak memory usage (MB): [0, 2]                 
+Total # Ops                     : 147                    
+Compute Unit(s)                 : NPU (147 ops)          
 ```
 
 
@@ -204,15 +221,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on ResNet101's performance across various devices [here](https://aihub.qualcomm.com/models/resnet101).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of ResNet101 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 ResNet101 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
 * [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)
 * [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]).