Upload README.md with huggingface_hub

README.md

@@ -18,7 +18,7 @@ tags:
 
 RegNet 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 RegNet found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/regnet.py).
+This model is an implementation of RegNet found [here]({source_repo}).
 This repository provides scripts to run RegNet on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/regnet).
@@ -33,15 +33,32 @@ More details on model performance across various devices, can be found
   - Number of parameters: 15.3M
   - Model size: 58.3 MB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| RegNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 2.075 ms | 0 - 7 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
+| RegNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.149 ms | 1 - 60 MB | FP16 | NPU | [RegNet.so](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.so) |
+| RegNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.197 ms | 0 - 42 MB | FP16 | NPU | [RegNet.onnx](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.onnx) |
+| RegNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 1.601 ms | 0 - 143 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
+| RegNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.652 ms | 1 - 27 MB | FP16 | NPU | [RegNet.so](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.so) |
+| RegNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.866 ms | 0 - 146 MB | FP16 | NPU | [RegNet.onnx](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.onnx) |
+| RegNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 2.041 ms | 0 - 2 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
+| RegNet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.036 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| RegNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 2.039 ms | 0 - 2 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
+| RegNet | SA8255 (Proxy) | SA8255P Proxy | QNN | 2.039 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
+| RegNet | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 2.037 ms | 0 - 15 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
+| RegNet | SA8775 (Proxy) | SA8775P Proxy | QNN | 2.028 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| RegNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 2.028 ms | 0 - 2 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
+| RegNet | SA8650 (Proxy) | SA8650P Proxy | QNN | 2.042 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| RegNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 2.808 ms | 0 - 125 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
+| RegNet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 2.905 ms | 1 - 22 MB | FP16 | NPU | Use Export Script |
+| RegNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.363 ms | 0 - 71 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
+| RegNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.448 ms | 0 - 28 MB | FP16 | NPU | Use Export Script |
+| RegNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.561 ms | 0 - 74 MB | FP16 | NPU | [RegNet.onnx](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.onnx) |
+| RegNet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.232 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
+| RegNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.208 ms | 40 - 40 MB | FP16 | NPU | [RegNet.onnx](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.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 | 2.067 ms | 0 - 2 MB | FP16 | NPU |  [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.125 ms | 0 - 70 MB | FP16 | NPU |  [RegNet.so](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.so) 
-
-
 
 ## Installation
 
@@ -96,16 +113,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.regnet.export
 ```
-
 ```
-Profile Job summary of RegNet
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 2.22 ms
-Estimated Peak Memory Range: 0.57-0.57 MB
-Compute Units: NPU (188) | Total (188)
-
-
+Profiling Results
+------------------------------------------------------------
+RegNet
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE                 
+Estimated inference time (ms)   : 2.1                    
+Estimated peak memory usage (MB): [0, 7]                 
+Total # Ops                     : 114                    
+Compute Unit(s)                 : NPU (114 ops)          
 ```
 
 
@@ -204,15 +221,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on RegNet's performance across various devices [here](https://aihub.qualcomm.com/models/regnet).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of RegNet 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 RegNet 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
 * [Designing Network Design Spaces](https://arxiv.org/abs/2003.13678)
 * [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/regnet.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:ai-hub-support@qti.qualcomm.com).