Upload README.md with huggingface_hub

README.md

@@ -14,7 +14,7 @@ tags:
 
 HRNet performs pose estimation in high-resolution representations.
 
-This model is an implementation of HRNetPose found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/hrnet_posenet).
+This model is an implementation of HRNetPose found [here]({source_repo}).
 This repository provides scripts to run HRNetPose on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/hrnet_pose).
@@ -29,15 +29,32 @@ More details on model performance across various devices, can be found
   - Number of parameters: 28.5M
   - Model size: 109 MB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| HRNetPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 2.847 ms | 0 - 2 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
+| HRNetPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.906 ms | 0 - 14 MB | FP16 | NPU | [HRNetPose.so](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.so) |
+| HRNetPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.91 ms | 0 - 677 MB | FP16 | NPU | [HRNetPose.onnx](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx) |
+| HRNetPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.292 ms | 0 - 121 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
+| HRNetPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.517 ms | 1 - 36 MB | FP16 | NPU | [HRNetPose.so](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.so) |
+| HRNetPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.455 ms | 0 - 148 MB | FP16 | NPU | [HRNetPose.onnx](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx) |
+| HRNetPose | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 2.838 ms | 0 - 2 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
+| HRNetPose | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.709 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| HRNetPose | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 2.835 ms | 0 - 2 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
+| HRNetPose | SA8255 (Proxy) | SA8255P Proxy | QNN | 2.717 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| HRNetPose | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 2.815 ms | 0 - 2 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
+| HRNetPose | SA8775 (Proxy) | SA8775P Proxy | QNN | 2.758 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| HRNetPose | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 2.843 ms | 0 - 2 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
+| HRNetPose | SA8650 (Proxy) | SA8650P Proxy | QNN | 2.748 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| HRNetPose | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 3.758 ms | 0 - 107 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
+| HRNetPose | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 3.885 ms | 1 - 27 MB | FP16 | NPU | Use Export Script |
+| HRNetPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.97 ms | 0 - 59 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
+| HRNetPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 2.035 ms | 1 - 34 MB | FP16 | NPU | Use Export Script |
+| HRNetPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.866 ms | 0 - 72 MB | FP16 | NPU | [HRNetPose.onnx](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx) |
+| HRNetPose | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.978 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
+| HRNetPose | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.972 ms | 57 - 57 MB | FP16 | NPU | [HRNetPose.onnx](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.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 | 2.886 ms | 0 - 356 MB | FP16 | NPU |  [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.964 ms | 1 - 16 MB | FP16 | NPU |  [HRNetPose.so](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.so) 
-
-
 
 ## Installation
 
@@ -93,16 +110,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.hrnet_pose.export
 ```
-
 ```
-Profile Job summary of HRNetPose
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 2.96 ms
-Estimated Peak Memory Range: 0.56-0.56 MB
-Compute Units: NPU (747) | Total (747)
-
-
+Profiling Results
+------------------------------------------------------------
+HRNetPose
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE                 
+Estimated inference time (ms)   : 2.8                    
+Estimated peak memory usage (MB): [0, 2]                 
+Total # Ops                     : 516                    
+Compute Unit(s)                 : NPU (516 ops)          
 ```
 
 
@@ -201,15 +218,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on HRNetPose's performance across various devices [here](https://aihub.qualcomm.com/models/hrnet_pose).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of HRNetPose can be found
-  [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf).
-- 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 HRNetPose can be found [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf).
+* 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 High-Resolution Representation Learning for Human Pose Estimation](https://arxiv.org/abs/1902.09212)
 * [Source Model Implementation](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/hrnet_posenet)
 
+
+
 ## 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).