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 2.50, ONNX Runtime 1.27.1	Download
ONNX	w8a16	Universal	QAIRT 2.50, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	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	0.925 ms	0 - 40 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.086 ms	0 - 43 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® X2 Elite	0.92 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	1.308 ms	0 - 61 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Gen 1 Mobile	3.182 ms	0 - 67 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	2.573 ms	1 - 6 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.774 ms	0 - 41 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® QCS8450	3.182 ms	0 - 67 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	2.335 ms	0 - 4 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	1.086 ms	0 - 43 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.762 ms	0 - 65 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.874 ms	0 - 62 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® X2 Elite	0.785 ms	1 - 1 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® X Elite	1.836 ms	20 - 20 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.21 ms	0 - 95 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	2.213 ms	0 - 93 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	6.417 ms	2 - 5 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	1.748 ms	0 - 4 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.779 ms	0 - 22 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® QCS8450	2.213 ms	0 - 93 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	1.905 ms	0 - 3 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	1.836 ms	20 - 20 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	12.29 ms	2 - 174 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	2.484 ms	0 - 167 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	0.874 ms	0 - 62 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	2.484 ms	0 - 167 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.941 ms	1 - 37 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.066 ms	1 - 36 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® X2 Elite	1.082 ms	1 - 1 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® X Elite	1.863 ms	1 - 1 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.304 ms	0 - 58 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	3.169 ms	0 - 65 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	2.515 ms	1 - 4 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.748 ms	1 - 2 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® QCS8450	3.169 ms	0 - 65 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	2.271 ms	3 - 6 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	1.863 ms	1 - 1 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	1.066 ms	1 - 36 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA7255P	7.56 ms	1 - 35 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA8295P	3.412 ms	0 - 38 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.997 ms	0 - 48 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.124 ms	0 - 46 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.367 ms	0 - 80 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	3.306 ms	0 - 88 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	2.863 ms	1 - 43 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.807 ms	0 - 3 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8775P	2.792 ms	0 - 51 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8650P	2.792 ms	0 - 51 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8255P	2.792 ms	0 - 51 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® QCS8450	3.306 ms	0 - 88 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	2.544 ms	0 - 41 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	1.124 ms	0 - 46 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA7255P	8.089 ms	1 - 50 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8295P	3.787 ms	1 - 51 MB	NPU

License

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

References

• RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.