Hugging Face's logo

qualcomm
/
RTMPose-Body2d

Keypoint Detection
PyTorch
android
Model card Files
xet
 Community

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 2.45, ONNX Runtime 1.25.0 Download
ONNX w8a16 Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a16 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 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
  • Number of parameters: 17.9M
  • Model size (float): 68.5 MB
  • Model size (w8a16): 18.2 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
RTMPose-Body2d ONNX float Snapdragon® X2 Elite 1.196 ms 2 - 2 MB NPU
RTMPose-Body2d ONNX float Snapdragon® X Elite 1.722 ms 37 - 37 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Gen 3 Mobile 1.336 ms 0 - 61 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Gen 1 Mobile 3.572 ms 1 - 65 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.782 ms 0 - 19 MB NPU
RTMPose-Body2d ONNX float Qualcomm® QCS8450 3.572 ms 1 - 65 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ IQ-9075 2.337 ms 0 - 4 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.937 ms 0 - 38 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Elite Mobile 1.065 ms 0 - 36 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ Q-8750 1.065 ms 0 - 36 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ IQ-X7181 1.722 ms 37 - 37 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® X2 Elite 0.898 ms 1 - 1 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® X Elite 1.745 ms 20 - 20 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1.135 ms 0 - 87 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 2.205 ms 0 - 90 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 5.825 ms 1 - 4 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.667 ms 0 - 22 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® QCS8450 2.205 ms 0 - 90 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 1.846 ms 0 - 3 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 2.28 ms 0 - 171 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.732 ms 0 - 60 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 11.865 ms 1 - 178 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Elite Mobile 0.856 ms 0 - 60 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 2.28 ms 0 - 171 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.856 ms 0 - 60 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.745 ms 20 - 20 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® X2 Elite 1.053 ms 1 - 1 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® X Elite 1.803 ms 1 - 1 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.317 ms 0 - 53 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Gen 1 Mobile 3.524 ms 0 - 62 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® QCS8275 7.475 ms 1 - 33 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.733 ms 1 - 3 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® SA8775P 2.447 ms 1 - 36 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® SA8650P 2.447 ms 1 - 36 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® SA8255P 2.447 ms 1 - 36 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® QCS8450 3.524 ms 0 - 62 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 2.572 ms 3 - 5 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.905 ms 1 - 35 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® SA7255P 7.475 ms 1 - 33 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Elite Mobile 1.069 ms 1 - 34 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® SA8295P 3.534 ms 0 - 35 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.069 ms 1 - 34 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.803 ms 1 - 1 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Snapdragon® X2 Elite 0.968 ms 0 - 0 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Snapdragon® X Elite 1.905 ms 0 - 0 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 1.197 ms 0 - 79 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® QCS8275 3.843 ms 0 - 48 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.695 ms 0 - 2 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® SA8775P 2.044 ms 0 - 51 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® SA8650P 2.044 ms 0 - 51 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® SA8255P 2.044 ms 0 - 51 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.882 ms 0 - 2 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.744 ms 0 - 51 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® SA7255P 3.843 ms 0 - 48 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.884 ms 0 - 52 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.884 ms 0 - 52 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.905 ms 0 - 0 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Gen 3 Mobile 1.26 ms 0 - 78 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Gen 1 Mobile 3.517 ms 0 - 86 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® QCS8275 7.473 ms 0 - 44 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.703 ms 0 - 3 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® SA8775P 2.38 ms 0 - 45 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® SA8650P 2.38 ms 0 - 45 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® SA8255P 2.38 ms 0 - 45 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® QCS8450 3.517 ms 0 - 86 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® Dragonwing™ IQ-9075 2.203 ms 0 - 40 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.902 ms 0 - 48 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® SA7255P 7.473 ms 0 - 44 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Elite Mobile 1.034 ms 0 - 47 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® SA8295P 3.511 ms 0 - 47 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® Dragonwing™ Q-8750 1.034 ms 0 - 47 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
Keypoint Detection
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/RTMPose-Body2d