Keypoint Detection
PyTorch
android

RTMPose-Body2d: Optimized for Qualcomm Devices

RTMPose is a machine learning model that detects human pose and returns a location and confidence for each of 133 joints.

This is based on the implementation of RTMPose-Body2d found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up 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 2.51, ONNX Runtime 1.30.0 Download
ONNX w8a16 Universal QAIRT 2.51, ONNX Runtime 1.30.0 Download
QNN_DLC float Universal QAIRT 2.51 Download
QNN_DLC w8a16 Universal QAIRT 2.51 Download
TFLITE float Universal QAIRT 2.51 Download

For more device-specific assets and performance metrics, visit RTMPose-Body2d on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models 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 RTMPose-Body2d on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.pose_estimation

Model Stats:

  • Input resolution: 256x192
  • Model size (float): 68.5 MB
  • Model size (w8a16): 18.2 MB
  • Number of parameters: 17.9M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
RTMPose-Body2d ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.941 ms 0 - 45 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.076 ms 0 - 42 MB NPU
RTMPose-Body2d ONNX float Snapdragon® X2 Elite 0.921 ms 2 - 2 MB NPU
RTMPose-Body2d ONNX float Snapdragon® X Elite 1.737 ms 37 - 37 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Gen 3 Mobile 1.306 ms 0 - 58 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Gen 1 Mobile 3.171 ms 0 - 70 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ IQ-8275 2.448 ms 1 - 6 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.786 ms 0 - 41 MB NPU
RTMPose-Body2d ONNX float Qualcomm® QCS8450 3.171 ms 0 - 70 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ IQ-9075 2.224 ms 0 - 5 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ IQ-X7181 1.737 ms 37 - 37 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ Q-8750 1.076 ms 0 - 42 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.841 ms 0 - 40 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Elite Gen 6 Mobile 0.921 ms 0 - 40 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.768 ms 0 - 65 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.872 ms 0 - 67 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® X2 Elite 0.789 ms 1 - 1 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® X Elite 1.834 ms 20 - 20 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1.213 ms 0 - 95 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 2.174 ms 0 - 95 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 6.42 ms 2 - 5 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 1.663 ms 0 - 4 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.775 ms 0 - 40 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® QCS8450 2.174 ms 0 - 95 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 1.79 ms 0 - 4 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.834 ms 20 - 20 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 12.252 ms 0 - 171 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 2.433 ms 0 - 167 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.872 ms 0 - 67 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 2.433 ms 0 - 167 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.555 ms 0 - 64 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Elite Gen 6 Mobile 0.705 ms 0 - 62 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.945 ms 1 - 39 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.093 ms 0 - 39 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® X2 Elite 1.079 ms 1 - 1 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® X Elite 1.843 ms 1 - 1 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.297 ms 0 - 54 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Gen 1 Mobile 3.158 ms 0 - 68 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 2.391 ms 1 - 5 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.752 ms 1 - 2 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® QCS8450 3.158 ms 0 - 68 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 2.172 ms 3 - 6 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.843 ms 1 - 1 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.093 ms 0 - 39 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® SA8295P 3.466 ms 0 - 40 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.848 ms 1 - 37 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Elite Gen 6 Mobile 0.913 ms 1 - 36 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.993 ms 0 - 52 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.12 ms 0 - 52 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Gen 3 Mobile 1.36 ms 0 - 75 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Gen 1 Mobile 3.311 ms 1 - 92 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® Dragonwing™ IQ-8275 2.565 ms 1 - 43 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.866 ms 1 - 3 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® SA8775P 19.727 ms 1 - 25 MB GPU
RTMPose-Body2d TFLITE float Qualcomm® SA8650P 19.727 ms 1 - 25 MB GPU
RTMPose-Body2d TFLITE float Qualcomm® SA8255P 19.727 ms 1 - 25 MB GPU
RTMPose-Body2d TFLITE float Qualcomm® QCS8450 3.311 ms 1 - 92 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® Dragonwing™ IQ-9075 2.333 ms 1 - 43 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® Dragonwing™ Q-8750 1.12 ms 0 - 52 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® SA7255P 35.082 ms 1 - 24 MB GPU
RTMPose-Body2d TFLITE float Qualcomm® SA8295P 3.783 ms 0 - 52 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.917 ms 0 - 48 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Elite Gen 6 Mobile 1.005 ms 0 - 48 MB NPU

License

  • The license for the original implementation of RTMPose-Body2d can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/RTMPose-Body2d