--- library_name: pytorch license: other tags: - android pipeline_tag: keypoint-detection --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_pose/web-assets/model_demo.png) # HRNetPose: Optimized for Mobile Deployment ## Perform accurate human pose estimation HRNet performs pose estimation in high-resolution representations. This model is an implementation of HRNetPose found [here](https://github.com/leoxiaobin/deep-high-resolution-net.pytorch). 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). ### Model Details - **Model Type:** Model_use_case.pose_estimation - **Model Stats:** - Model checkpoint: hrnet_posenet_FP32_state_dict - Input resolution: 256x192 - Number of parameters: 28.5M - Model size (float): 109 MB - Model size (w8a8): 28.1 MB | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |---|---|---|---|---|---|---|---|---| | HRNetPose | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 14.342 ms | 0 - 79 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) | | HRNetPose | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 14.17 ms | 1 - 42 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 3.64 ms | 0 - 122 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) | | HRNetPose | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 4.857 ms | 0 - 57 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.668 ms | 0 - 19 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) | | HRNetPose | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.614 ms | 1 - 16 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2.69 ms | 0 - 125 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx.zip) | | HRNetPose | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 4.348 ms | 0 - 80 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) | | HRNetPose | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.265 ms | 0 - 41 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 14.342 ms | 0 - 79 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) | | HRNetPose | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 14.17 ms | 1 - 42 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 2.618 ms | 0 - 28 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) | | HRNetPose | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 2.615 ms | 1 - 14 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 4.514 ms | 0 - 73 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) | | HRNetPose | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 4.512 ms | 1 - 41 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 2.623 ms | 0 - 18 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) | | HRNetPose | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 2.611 ms | 1 - 17 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 4.348 ms | 0 - 80 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) | | HRNetPose | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 4.265 ms | 0 - 41 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.893 ms | 0 - 120 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) | | HRNetPose | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.984 ms | 1 - 58 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.008 ms | 0 - 81 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx.zip) | | HRNetPose | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 1.568 ms | 0 - 83 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) | | HRNetPose | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.554 ms | 1 - 50 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1.687 ms | 0 - 51 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx.zip) | | HRNetPose | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 1.315 ms | 0 - 81 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) | | HRNetPose | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 1.279 ms | 1 - 49 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 1.422 ms | 1 - 54 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx.zip) | | HRNetPose | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.851 ms | 95 - 95 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.dlc) | | HRNetPose | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.725 ms | 55 - 55 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx.zip) | | HRNetPose | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 5.203 ms | 0 - 67 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 2.772 ms | 0 - 95 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1.903 ms | 0 - 16 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 2.326 ms | 0 - 67 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 8.852 ms | 0 - 97 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 200.644 ms | 18 - 46 MB | CPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.onnx.zip) | | HRNetPose | w8a16 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 206.888 ms | 15 - 45 MB | CPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.onnx.zip) | | HRNetPose | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 5.203 ms | 0 - 67 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 1.913 ms | 0 - 21 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 3.017 ms | 0 - 74 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 1.892 ms | 0 - 16 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 2.326 ms | 0 - 67 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.386 ms | 0 - 92 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.018 ms | 0 - 74 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 99.225 ms | 220 - 1918 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.onnx.zip) | | HRNetPose | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | QNN_DLC | 2.582 ms | 0 - 72 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | ONNX | 212.813 ms | 16 - 42 MB | CPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.onnx.zip) | | HRNetPose | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.81 ms | 0 - 69 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 121.702 ms | 217 - 1858 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.onnx.zip) | | HRNetPose | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.174 ms | 122 - 122 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.dlc) | | HRNetPose | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 148.42 ms | 232 - 232 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a16.onnx.zip) | | HRNetPose | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 2.603 ms | 0 - 64 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 2.852 ms | 0 - 66 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 1.244 ms | 0 - 101 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 1.695 ms | 0 - 91 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 0.956 ms | 0 - 160 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1.159 ms | 0 - 66 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 65.605 ms | 108 - 363 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.onnx.zip) | | HRNetPose | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 1.331 ms | 0 - 64 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 1.472 ms | 0 - 66 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 3.715 ms | 0 - 79 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 5.48 ms | 0 - 91 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 136.947 ms | 15 - 42 MB | CPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.onnx.zip) | | HRNetPose | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 17.259 ms | 0 - 3 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 128.915 ms | 11 - 45 MB | CPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.onnx.zip) | | HRNetPose | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 2.603 ms | 0 - 64 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 2.852 ms | 0 - 66 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 0.956 ms | 0 - 161 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 1.171 ms | 0 - 18 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 1.636 ms | 0 - 70 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 1.87 ms | 0 - 72 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 0.963 ms | 0 - 163 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 1.148 ms | 0 - 71 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 1.331 ms | 0 - 64 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 1.472 ms | 0 - 66 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.675 ms | 0 - 97 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.83 ms | 0 - 90 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 48.232 ms | 142 - 2112 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.onnx.zip) | | HRNetPose | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 0.573 ms | 0 - 71 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.628 ms | 0 - 73 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 44.117 ms | 144 - 919 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.onnx.zip) | | HRNetPose | w8a8 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | TFLITE | 1.4 ms | 0 - 68 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | QNN_DLC | 1.552 ms | 0 - 71 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | ONNX | 140.006 ms | 14 - 39 MB | CPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.onnx.zip) | | HRNetPose | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 0.544 ms | 0 - 68 MB | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.tflite) | | HRNetPose | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.593 ms | 0 - 73 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 43.64 ms | 143 - 926 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.onnx.zip) | | HRNetPose | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.291 ms | 135 - 135 MB | NPU | [HRNetPose.dlc](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.dlc) | | HRNetPose | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 59.983 ms | 116 - 116 MB | NPU | [HRNetPose.onnx.zip](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose_w8a8.onnx.zip) | ## Installation Install the package via pip: ```bash pip install "qai-hub-models[hrnet-pose]" torch==2.4.1 --trusted-host download.openmmlab.com -f https://download.openmmlab.com/mmcv/dist/cpu/torch2.4/index.html -f https://qaihub-public-python-wheels.s3.us-west-2.amazonaws.com/index.html ``` ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`. With this API token, you can configure your client to run models on the cloud hosted devices. ```bash qai-hub configure --api_token API_TOKEN ``` Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information. ## Demo off target The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input. ```bash python -m qai_hub_models.models.hrnet_pose.demo ``` The above demo runs a reference implementation of pre-processing, model inference, and post processing. **NOTE**: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above). ``` %run -m qai_hub_models.models.hrnet_pose.demo ``` ### Run model on a cloud-hosted device In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following: * Performance check on-device on a cloud-hosted device * Downloads compiled assets that can be deployed on-device for Android. * Accuracy check between PyTorch and on-device outputs. ```bash python -m qai_hub_models.models.hrnet_pose.export ``` ## How does this work? This [export script](https://aihub.qualcomm.com/models/hrnet_pose/qai_hub_models/models/HRNetPose/export.py) leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model on-device. Lets go through each step below in detail: Step 1: **Compile model for on-device deployment** To compile a PyTorch model for on-device deployment, we first trace the model in memory using the `jit.trace` and then call the `submit_compile_job` API. ```python import torch import qai_hub as hub from qai_hub_models.models.hrnet_pose import Model # Load the model torch_model = Model.from_pretrained() # Device device = hub.Device("Samsung Galaxy S25") # Trace model input_shape = torch_model.get_input_spec() sample_inputs = torch_model.sample_inputs() pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()]) # Compile model on a specific device compile_job = hub.submit_compile_job( model=pt_model, device=device, input_specs=torch_model.get_input_spec(), ) # Get target model to run on-device target_model = compile_job.get_target_model() ``` Step 2: **Performance profiling on cloud-hosted device** After compiling models from step 1. Models can be profiled model on-device using the `target_model`. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics. ```python profile_job = hub.submit_profile_job( model=target_model, device=device, ) ``` Step 3: **Verify on-device accuracy** To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device. ```python input_data = torch_model.sample_inputs() inference_job = hub.submit_inference_job( model=target_model, device=device, inputs=input_data, ) on_device_output = inference_job.download_output_data() ``` With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output. **Note**: This on-device profiling and inference requires access to Qualcomm® AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup). ## Run demo on a cloud-hosted device You can also run the demo on-device. ```bash python -m qai_hub_models.models.hrnet_pose.demo --eval-mode on-device ``` **NOTE**: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above). ``` %run -m qai_hub_models.models.hrnet_pose.demo -- --eval-mode on-device ``` ## Deploying compiled model to Android The models can be deployed using multiple runtimes: - TensorFlow Lite (`.tflite` export): [This tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a guide to deploy the .tflite model in an Android application. - QNN (`.so` export ): This [sample app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html) provides instructions on how to use the `.so` shared library in an Android application. ## View on Qualcomm® AI Hub 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/leoxiaobin/deep-high-resolution-net.pytorch/blob/master/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 High-Resolution Representation Learning for Human Pose Estimation](https://arxiv.org/abs/1902.09212) * [Source Model Implementation](https://github.com/leoxiaobin/deep-high-resolution-net.pytorch) ## 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).