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 1.27.1 Download
ONNX w8a16 Universal QAIRT 2.45, ONNX Runtime 1.27.1 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
  • 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® X2 Elite 0.935 ms 2 - 2 MB NPU
RTMPose-Body2d ONNX float Snapdragon® X Elite 1.792 ms 38 - 38 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Gen 3 Mobile 1.386 ms 0 - 60 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Gen 1 Mobile 3.659 ms 0 - 66 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ IQ-8275 2.635 ms 1 - 5 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.817 ms 0 - 159 MB NPU
RTMPose-Body2d ONNX float Qualcomm® QCS8450 3.659 ms 0 - 66 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ IQ-9075 2.34 ms 0 - 4 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ IQ-X7181 1.792 ms 38 - 38 MB NPU
RTMPose-Body2d ONNX float Qualcomm® Dragonwing™ Q-8750 1.103 ms 0 - 38 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Elite Mobile 1.103 ms 0 - 38 MB NPU
RTMPose-Body2d ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.951 ms 0 - 42 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® X2 Elite 0.791 ms 1 - 1 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® X Elite 1.82 ms 19 - 19 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1.193 ms 0 - 90 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 2.309 ms 0 - 89 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 7.502 ms 2 - 5 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 1.791 ms 0 - 4 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.775 ms 0 - 22 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® QCS8450 2.309 ms 0 - 89 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 1.89 ms 0 - 3 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.82 ms 19 - 19 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 12.349 ms 2 - 179 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 2.5 ms 0 - 174 MB NPU
RTMPose-Body2d ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.894 ms 0 - 63 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Elite Mobile 0.894 ms 0 - 63 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.763 ms 0 - 61 MB NPU
RTMPose-Body2d ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 2.5 ms 0 - 174 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® X2 Elite 1.124 ms 1 - 1 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® X Elite 1.865 ms 1 - 1 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.363 ms 0 - 56 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Gen 1 Mobile 3.611 ms 0 - 63 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 2.52 ms 1 - 4 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.798 ms 1 - 2 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® SA8775P 2.435 ms 1 - 35 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® SA8650P 2.435 ms 1 - 35 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® SA8255P 2.435 ms 1 - 35 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® QCS8450 3.611 ms 0 - 63 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 2.284 ms 3 - 5 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.865 ms 1 - 1 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.102 ms 0 - 31 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® SA7255P 7.613 ms 1 - 32 MB NPU
RTMPose-Body2d QNN_DLC float Qualcomm® SA8295P 3.612 ms 1 - 35 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Elite Mobile 1.102 ms 0 - 31 MB NPU
RTMPose-Body2d QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.943 ms 1 - 35 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Snapdragon® X2 Elite 0.944 ms 0 - 0 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Snapdragon® X Elite 1.909 ms 0 - 0 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 1.182 ms 0 - 79 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 1.711 ms 0 - 3 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.689 ms 0 - 2 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® SA8775P 2.043 ms 0 - 51 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® SA8650P 2.043 ms 0 - 51 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® SA8255P 2.043 ms 0 - 51 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.895 ms 0 - 2 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.909 ms 0 - 0 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.88 ms 0 - 48 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Qualcomm® SA7255P 3.832 ms 0 - 49 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.88 ms 0 - 48 MB NPU
RTMPose-Body2d QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.741 ms 0 - 46 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Gen 3 Mobile 1.377 ms 0 - 78 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Gen 1 Mobile 3.777 ms 1 - 87 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® Dragonwing™ IQ-8275 2.84 ms 1 - 43 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.859 ms 1 - 4 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® SA8775P 2.83 ms 0 - 47 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® SA8650P 2.83 ms 0 - 47 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® SA8255P 2.83 ms 0 - 47 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® QCS8450 3.777 ms 1 - 87 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® Dragonwing™ IQ-9075 2.554 ms 1 - 42 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® Dragonwing™ Q-8750 1.157 ms 0 - 47 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® SA7255P 8.104 ms 1 - 45 MB NPU
RTMPose-Body2d TFLITE float Qualcomm® SA8295P 4.105 ms 0 - 47 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Elite Mobile 1.157 ms 0 - 47 MB NPU
RTMPose-Body2d TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.992 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