---
library_name: pytorch
license: other
tags:
- bu_auto
- 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 Qualcomm Devices

HRNet performs pose estimation in high-resolution representations.

This is based on the implementation of HRNetPose found [here](https://github.com/leoxiaobin/deep-high-resolution-net.pytorch).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/hrnet_pose) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.

## Getting Started
There are two ways to deploy this model on your device:

### Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_pose/releases/v0.54.0/hrnet_pose-onnx-float.zip)
| ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_pose/releases/v0.54.0/hrnet_pose-onnx-w8a16.zip)
| ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_pose/releases/v0.54.0/hrnet_pose-onnx-w8a8.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_pose/releases/v0.54.0/hrnet_pose-qnn_dlc-float.zip)
| QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_pose/releases/v0.54.0/hrnet_pose-qnn_dlc-w8a16.zip)
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_pose/releases/v0.54.0/hrnet_pose-qnn_dlc-w8a8.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_pose/releases/v0.54.0/hrnet_pose-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_pose/releases/v0.54.0/hrnet_pose-tflite-w8a8.zip)

For more device-specific assets and performance metrics, visit **[HRNetPose on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/hrnet_pose)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/hrnet_pose) Python library to compile and export the model with your own:
- Custom weights (e.g., fine-tuned checkpoints)
- Custom input shapes
- Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for [HRNetPose on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/hrnet_pose) for usage instructions.

## 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

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| HRNetPose | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.216 ms | 1 - 91 MB | NPU
| HRNetPose | ONNX | float | Snapdragon® 8 Elite Mobile | 1.5 ms | 0 - 93 MB | NPU
| HRNetPose | ONNX | float | Snapdragon® X2 Elite | 1.328 ms | 55 - 55 MB | NPU
| HRNetPose | ONNX | float | Snapdragon® X Elite | 2.62 ms | 55 - 55 MB | NPU
| HRNetPose | ONNX | float | Snapdragon® X Elite | 2.62 ms | 55 - 55 MB | NPU
| HRNetPose | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.865 ms | 0 - 148 MB | NPU
| HRNetPose | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.423 ms | 0 - 58 MB | NPU
| HRNetPose | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.5 ms | 0 - 93 MB | NPU
| HRNetPose | ONNX | float | Qualcomm® QCS9075 | 3.932 ms | 0 - 4 MB | NPU
| HRNetPose | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.78 ms | 0 - 129 MB | NPU
| HRNetPose | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 0.969 ms | 0 - 132 MB | NPU
| HRNetPose | ONNX | w8a16 | Snapdragon® X2 Elite | 1.012 ms | 28 - 28 MB | NPU
| HRNetPose | ONNX | w8a16 | Snapdragon® X Elite | 1.973 ms | 28 - 28 MB | NPU
| HRNetPose | ONNX | w8a16 | Snapdragon® X Elite | 1.973 ms | 28 - 28 MB | NPU
| HRNetPose | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.285 ms | 0 - 200 MB | NPU
| HRNetPose | ONNX | w8a16 | Qualcomm® QCS6490 | 485.217 ms | 30 - 34 MB | CPU
| HRNetPose | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 1.731 ms | 0 - 37 MB | NPU
| HRNetPose | ONNX | w8a16 | Qualcomm® QCM6690 | 220.032 ms | 31 - 50 MB | CPU
| HRNetPose | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 214.581 ms | 25 - 39 MB | CPU
| HRNetPose | ONNX | w8a16 | Qualcomm® QCS9075 | 1.998 ms | 0 - 3 MB | NPU
| HRNetPose | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.969 ms | 0 - 132 MB | NPU
| HRNetPose | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 214.581 ms | 25 - 39 MB | CPU
| HRNetPose | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.8 ms | 0 - 123 MB | NPU
| HRNetPose | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.912 ms | 0 - 124 MB | NPU
| HRNetPose | ONNX | w8a8 | Snapdragon® X2 Elite | 0.766 ms | 30 - 30 MB | NPU
| HRNetPose | ONNX | w8a8 | Snapdragon® X Elite | 1.634 ms | 28 - 28 MB | NPU
| HRNetPose | ONNX | w8a8 | Snapdragon® X Elite | 1.634 ms | 28 - 28 MB | NPU
| HRNetPose | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.047 ms | 0 - 185 MB | NPU
| HRNetPose | ONNX | w8a8 | Qualcomm® QCS6490 | 89.943 ms | 8 - 69 MB | CPU
| HRNetPose | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.49 ms | 0 - 5 MB | NPU
| HRNetPose | ONNX | w8a8 | Qualcomm® QCS9075 | 1.539 ms | 0 - 3 MB | NPU
| HRNetPose | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 58.739 ms | 9 - 31 MB | CPU
| HRNetPose | ONNX | w8a8 | Qualcomm® QCM6690 | 60.899 ms | 9 - 35 MB | CPU
| HRNetPose | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.912 ms | 0 - 124 MB | NPU
| HRNetPose | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 58.739 ms | 9 - 31 MB | CPU
| HRNetPose | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.267 ms | 0 - 77 MB | NPU
| HRNetPose | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.567 ms | 0 - 73 MB | NPU
| HRNetPose | QNN_DLC | float | Snapdragon® X2 Elite | 1.657 ms | 1 - 1 MB | NPU
| HRNetPose | QNN_DLC | float | Snapdragon® X Elite | 2.922 ms | 1 - 1 MB | NPU
| HRNetPose | QNN_DLC | float | Snapdragon® X Elite | 2.922 ms | 1 - 1 MB | NPU
| HRNetPose | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.992 ms | 0 - 116 MB | NPU
| HRNetPose | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 2.735 ms | 1 - 3 MB | NPU
| HRNetPose | QNN_DLC | float | Qualcomm® SA8775P | 4.312 ms | 1 - 74 MB | NPU
| HRNetPose | QNN_DLC | float | Qualcomm® SA8775P | 4.312 ms | 1 - 74 MB | NPU
| HRNetPose | QNN_DLC | float | Qualcomm® SA8775P | 4.312 ms | 1 - 74 MB | NPU
| HRNetPose | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 5.013 ms | 0 - 103 MB | NPU
| HRNetPose | QNN_DLC | float | Qualcomm® SA7255P | 14.169 ms | 1 - 73 MB | NPU
| HRNetPose | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.567 ms | 0 - 73 MB | NPU
| HRNetPose | QNN_DLC | float | Qualcomm® SA8295P | 4.59 ms | 1 - 61 MB | NPU
| HRNetPose | QNN_DLC | float | Qualcomm® QCS9075 | 4.107 ms | 1 - 3 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.809 ms | 0 - 101 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 0.997 ms | 0 - 101 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 1.303 ms | 0 - 0 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Snapdragon® X Elite | 2.105 ms | 0 - 0 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Snapdragon® X Elite | 2.105 ms | 0 - 0 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.397 ms | 0 - 146 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 6.677 ms | 0 - 2 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 1.884 ms | 0 - 9 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Qualcomm® SA8775P | 2.255 ms | 0 - 102 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Qualcomm® SA8775P | 2.255 ms | 0 - 102 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Qualcomm® SA8775P | 2.255 ms | 0 - 102 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 21.183 ms | 0 - 217 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 2.745 ms | 0 - 150 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 2.55 ms | 0 - 101 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 2.185 ms | 0 - 2 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Qualcomm® SA7255P | 5.164 ms | 0 - 100 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.997 ms | 0 - 101 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Qualcomm® SA8295P | 3.069 ms | 0 - 99 MB | NPU
| HRNetPose | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 2.55 ms | 0 - 101 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.567 ms | 0 - 94 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.638 ms | 0 - 95 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.711 ms | 0 - 0 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.267 ms | 0 - 0 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.267 ms | 0 - 0 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.819 ms | 0 - 133 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 3.719 ms | 0 - 2 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.13 ms | 0 - 2 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.496 ms | 0 - 91 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.496 ms | 0 - 91 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.496 ms | 0 - 91 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.284 ms | 0 - 2 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.736 ms | 0 - 137 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.509 ms | 0 - 89 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 10.435 ms | 0 - 213 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.638 ms | 0 - 95 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Qualcomm® SA7255P | 2.839 ms | 0 - 90 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.964 ms | 0 - 88 MB | NPU
| HRNetPose | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.509 ms | 0 - 89 MB | NPU
| HRNetPose | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.28 ms | 0 - 113 MB | NPU
| HRNetPose | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.55 ms | 0 - 115 MB | NPU
| HRNetPose | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.986 ms | 0 - 185 MB | NPU
| HRNetPose | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.781 ms | 0 - 2 MB | NPU
| HRNetPose | TFLITE | float | Qualcomm® SA8775P | 4.33 ms | 0 - 112 MB | NPU
| HRNetPose | TFLITE | float | Qualcomm® SA8775P | 4.33 ms | 0 - 112 MB | NPU
| HRNetPose | TFLITE | float | Qualcomm® SA8775P | 4.33 ms | 0 - 112 MB | NPU
| HRNetPose | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5.035 ms | 0 - 172 MB | NPU
| HRNetPose | TFLITE | float | Qualcomm® SA7255P | 14.142 ms | 0 - 111 MB | NPU
| HRNetPose | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.55 ms | 0 - 115 MB | NPU
| HRNetPose | TFLITE | float | Qualcomm® SA8295P | 4.638 ms | 0 - 103 MB | NPU
| HRNetPose | TFLITE | float | Qualcomm® QCS9075 | 4.133 ms | 0 - 58 MB | NPU
| HRNetPose | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.502 ms | 0 - 91 MB | NPU
| HRNetPose | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.596 ms | 0 - 88 MB | NPU
| HRNetPose | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.715 ms | 0 - 138 MB | NPU
| HRNetPose | TFLITE | w8a8 | Qualcomm® QCS6490 | 3.475 ms | 0 - 30 MB | NPU
| HRNetPose | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.954 ms | 0 - 2 MB | NPU
| HRNetPose | TFLITE | w8a8 | Qualcomm® SA8775P | 1.364 ms | 0 - 89 MB | NPU
| HRNetPose | TFLITE | w8a8 | Qualcomm® SA8775P | 1.364 ms | 0 - 89 MB | NPU
| HRNetPose | TFLITE | w8a8 | Qualcomm® SA8775P | 1.364 ms | 0 - 89 MB | NPU
| HRNetPose | TFLITE | w8a8 | Qualcomm® QCS9075 | 1.082 ms | 0 - 30 MB | NPU
| HRNetPose | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.522 ms | 0 - 140 MB | NPU
| HRNetPose | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.359 ms | 0 - 86 MB | NPU
| HRNetPose | TFLITE | w8a8 | Qualcomm® QCM6690 | 9.614 ms | 0 - 204 MB | NPU
| HRNetPose | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.596 ms | 0 - 88 MB | NPU
| HRNetPose | TFLITE | w8a8 | Qualcomm® SA7255P | 2.579 ms | 0 - 86 MB | NPU
| HRNetPose | TFLITE | w8a8 | Qualcomm® SA8295P | 1.767 ms | 0 - 85 MB | NPU
| HRNetPose | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.359 ms | 0 - 86 MB | NPU

## 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).

## 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).