HRNetFace: Optimized for Qualcomm Devices

Detects attributes (liveness, eye closeness, mask presence, glasses presence, sunglasses presence) that apply to a given face.

This is based on the implementation of HRNetFace 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 1.24.1	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.17.0	Download

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

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

• Model checkpoint: HR18-COFW.pth
• Input resolution: 256x256
• Number of parameters: 9.68M
• Model size (float): 36.87MB
• Model size (w8a8): 17.7 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
HRNetFace	ONNX	float	Snapdragon® X2 Elite	1.54 ms	31 - 31 MB	NPU
HRNetFace	ONNX	float	Snapdragon® X Elite	3.34 ms	30 - 30 MB	NPU
HRNetFace	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.156 ms	0 - 156 MB	NPU
HRNetFace	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.97 ms	0 - 34 MB	NPU
HRNetFace	ONNX	float	Qualcomm® QCS9075	4.741 ms	2 - 4 MB	NPU
HRNetFace	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.653 ms	0 - 98 MB	NPU
HRNetFace	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.328 ms	1 - 98 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® X2 Elite	0.654 ms	15 - 15 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® X Elite	1.542 ms	15 - 15 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.899 ms	0 - 153 MB	NPU
HRNetFace	ONNX	w8a8	Qualcomm® QCS6490	97.024 ms	18 - 36 MB	CPU
HRNetFace	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	1.298 ms	0 - 21 MB	NPU
HRNetFace	ONNX	w8a8	Qualcomm® QCS9075	1.523 ms	0 - 3 MB	NPU
HRNetFace	ONNX	w8a8	Qualcomm® QCM6690	49.948 ms	21 - 40 MB	CPU
HRNetFace	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.702 ms	0 - 103 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	46.986 ms	18 - 37 MB	CPU
HRNetFace	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.587 ms	0 - 104 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® X2 Elite	1.932 ms	1 - 1 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® X Elite	3.721 ms	1 - 1 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.339 ms	0 - 123 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	15.449 ms	1 - 77 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.319 ms	1 - 2 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® SA8775P	5.1 ms	1 - 80 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® QCS9075	5.029 ms	1 - 4 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	5.434 ms	0 - 107 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® SA7255P	15.449 ms	1 - 77 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® SA8295P	5.593 ms	1 - 62 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.758 ms	0 - 80 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.369 ms	1 - 83 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.849 ms	0 - 0 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® X Elite	1.563 ms	0 - 0 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.906 ms	0 - 110 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS6490	3.77 ms	0 - 2 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	3.252 ms	0 - 70 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	1.35 ms	0 - 115 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® SA8775P	1.702 ms	0 - 72 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS9075	1.616 ms	0 - 2 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCM6690	10.476 ms	0 - 197 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	1.78 ms	0 - 106 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® SA7255P	3.252 ms	0 - 70 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® SA8295P	2.21 ms	0 - 68 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.659 ms	0 - 72 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.619 ms	0 - 78 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.541 ms	0 - 72 MB	NPU
HRNetFace	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.321 ms	0 - 144 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® QCS8275 (Proxy)	15.414 ms	0 - 93 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.333 ms	0 - 2 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® SA8775P	5.168 ms	0 - 94 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® QCS9075	5.041 ms	0 - 35 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® QCS8450 (Proxy)	5.433 ms	1 - 129 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® SA7255P	15.414 ms	0 - 93 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® SA8295P	5.659 ms	1 - 75 MB	NPU
HRNetFace	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.757 ms	0 - 89 MB	NPU
HRNetFace	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.381 ms	0 - 99 MB	NPU
HRNetFace	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.736 ms	0 - 113 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS6490	3.343 ms	0 - 18 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	2.895 ms	0 - 71 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	1.109 ms	0 - 3 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® SA8775P	5.606 ms	0 - 70 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS9075	1.326 ms	0 - 18 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCM6690	9.802 ms	0 - 198 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	1.596 ms	0 - 111 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® SA7255P	2.895 ms	0 - 71 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® SA8295P	1.949 ms	0 - 68 MB	NPU
HRNetFace	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.583 ms	0 - 72 MB	NPU
HRNetFace	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.354 ms	0 - 75 MB	NPU
HRNetFace	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.465 ms	0 - 74 MB	NPU

License

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

References

• Deep High-Resolution Representation Learning for Visual Recognition
• 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.