LiteHRNet: Optimized for Qualcomm Devices

LiteHRNet is a machine learning model that detects human pose and returns a location and confidence for each of 17 joints.

This is based on the implementation of LiteHRNet 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 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit LiteHRNet 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 LiteHRNet on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.pose_estimation

Model Stats:

• Input resolution: 256x192
• Number of parameters: 1.11M
• Model size (float): 4.49 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
LiteHRNet	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2.734 ms	1 - 99 MB	NPU
LiteHRNet	ONNX	float	Snapdragon® 8 Elite Mobile	2.839 ms	0 - 100 MB	NPU
LiteHRNet	ONNX	float	Snapdragon® X2 Elite	2.839 ms	5 - 5 MB	NPU
LiteHRNet	ONNX	float	Snapdragon® X Elite	5.729 ms	5 - 5 MB	NPU
LiteHRNet	ONNX	float	Snapdragon® X Elite	5.729 ms	5 - 5 MB	NPU
LiteHRNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.121 ms	0 - 120 MB	NPU
LiteHRNet	ONNX	float	Qualcomm® QCS8550 (Proxy)	5.209 ms	0 - 11 MB	NPU
LiteHRNet	ONNX	float	Qualcomm® QCS9075	5.877 ms	1 - 4 MB	NPU
LiteHRNet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	2.839 ms	0 - 100 MB	NPU
LiteHRNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.857 ms	1 - 83 MB	NPU
LiteHRNet	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.023 ms	1 - 82 MB	NPU
LiteHRNet	QNN_DLC	float	Snapdragon® X2 Elite	1.24 ms	1 - 1 MB	NPU
LiteHRNet	QNN_DLC	float	Snapdragon® X Elite	2.375 ms	1 - 1 MB	NPU
LiteHRNet	QNN_DLC	float	Snapdragon® X Elite	2.375 ms	1 - 1 MB	NPU
LiteHRNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.319 ms	0 - 103 MB	NPU
LiteHRNet	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	4.953 ms	1 - 79 MB	NPU
LiteHRNet	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	2.108 ms	1 - 90 MB	NPU
LiteHRNet	QNN_DLC	float	Qualcomm® SA8775P	2.636 ms	1 - 80 MB	NPU
LiteHRNet	QNN_DLC	float	Qualcomm® SA8775P	2.636 ms	1 - 80 MB	NPU
LiteHRNet	QNN_DLC	float	Qualcomm® SA8775P	2.636 ms	1 - 80 MB	NPU
LiteHRNet	QNN_DLC	float	Qualcomm® QCS9075	2.482 ms	1 - 3 MB	NPU
LiteHRNet	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	2.874 ms	0 - 103 MB	NPU
LiteHRNet	QNN_DLC	float	Qualcomm® SA7255P	4.953 ms	1 - 79 MB	NPU
LiteHRNet	QNN_DLC	float	Qualcomm® SA8295P	3.391 ms	1 - 82 MB	NPU
LiteHRNet	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.023 ms	1 - 82 MB	NPU
LiteHRNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.99 ms	0 - 117 MB	NPU
LiteHRNet	TFLITE	float	Snapdragon® 8 Elite Mobile	2.194 ms	0 - 120 MB	NPU
LiteHRNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.637 ms	0 - 151 MB	NPU
LiteHRNet	TFLITE	float	Qualcomm® QCS8275 (Proxy)	8.512 ms	0 - 114 MB	NPU
LiteHRNet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	4.157 ms	0 - 3 MB	NPU
LiteHRNet	TFLITE	float	Qualcomm® SA8775P	5.125 ms	0 - 115 MB	NPU
LiteHRNet	TFLITE	float	Qualcomm® SA8775P	5.125 ms	0 - 115 MB	NPU
LiteHRNet	TFLITE	float	Qualcomm® SA8775P	5.125 ms	0 - 115 MB	NPU
LiteHRNet	TFLITE	float	Qualcomm® QCS9075	5.076 ms	0 - 10 MB	NPU
LiteHRNet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	5.234 ms	0 - 140 MB	NPU
LiteHRNet	TFLITE	float	Qualcomm® SA7255P	8.512 ms	0 - 114 MB	NPU
LiteHRNet	TFLITE	float	Qualcomm® SA8295P	6.205 ms	0 - 111 MB	NPU
LiteHRNet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.194 ms	0 - 120 MB	NPU

License

• The license for the original implementation of LiteHRNet can be found here.

References

• Lite-HRNet: A Lightweight High-Resolution Network
• 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.