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 1.24.3	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a8	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download
TFLITE	w8a8	Universal	QAIRT 2.45	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® 8 Elite Gen 5 Mobile	1.323 ms	1 - 98 MB	NPU
HRNetFace	ONNX	float	Snapdragon® X2 Elite	1.527 ms	31 - 31 MB	NPU
HRNetFace	ONNX	float	Snapdragon® X Elite	3.336 ms	30 - 30 MB	NPU
HRNetFace	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.153 ms	0 - 155 MB	NPU
HRNetFace	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.976 ms	0 - 34 MB	NPU
HRNetFace	ONNX	float	Qualcomm® QCS9075	4.752 ms	2 - 4 MB	NPU
HRNetFace	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.648 ms	0 - 97 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.588 ms	0 - 105 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® X2 Elite	0.655 ms	15 - 15 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® X Elite	1.543 ms	15 - 15 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.91 ms	0 - 152 MB	NPU
HRNetFace	ONNX	w8a8	Qualcomm® QCS6490	91.333 ms	18 - 36 MB	CPU
HRNetFace	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	1.345 ms	0 - 21 MB	NPU
HRNetFace	ONNX	w8a8	Qualcomm® QCS9075	1.53 ms	0 - 3 MB	NPU
HRNetFace	ONNX	w8a8	Qualcomm® QCM6690	49.821 ms	18 - 36 MB	CPU
HRNetFace	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.703 ms	0 - 105 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	46.758 ms	17 - 35 MB	CPU
HRNetFace	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.383 ms	1 - 81 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® X2 Elite	1.937 ms	1 - 1 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® X Elite	3.693 ms	1 - 1 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.305 ms	1 - 122 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	15.432 ms	1 - 75 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.276 ms	1 - 3 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® SA8775P	5.098 ms	1 - 79 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® QCS9075	5.02 ms	1 - 4 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	5.502 ms	0 - 104 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® SA7255P	15.432 ms	1 - 75 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® SA8295P	5.64 ms	0 - 62 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.756 ms	0 - 79 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.54 ms	0 - 74 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.842 ms	0 - 0 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® X Elite	1.554 ms	0 - 0 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.915 ms	0 - 108 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS6490	3.853 ms	0 - 2 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	3.265 ms	0 - 71 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	1.363 ms	0 - 2 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® SA8775P	1.716 ms	0 - 72 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS9075	1.611 ms	0 - 2 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCM6690	10.627 ms	0 - 200 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	1.841 ms	0 - 108 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® SA7255P	3.265 ms	0 - 71 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® SA8295P	2.222 ms	0 - 70 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.69 ms	0 - 74 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.645 ms	0 - 80 MB	NPU
HRNetFace	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.378 ms	0 - 96 MB	NPU
HRNetFace	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.337 ms	0 - 135 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® QCS8275 (Proxy)	15.489 ms	0 - 93 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.357 ms	0 - 2 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® SA8775P	5.129 ms	0 - 92 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® QCS9075	5.052 ms	0 - 35 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® QCS8450 (Proxy)	5.488 ms	0 - 124 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® SA7255P	15.489 ms	0 - 93 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® SA8295P	5.65 ms	1 - 74 MB	NPU
HRNetFace	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.765 ms	0 - 96 MB	NPU
HRNetFace	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.457 ms	0 - 75 MB	NPU
HRNetFace	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.752 ms	0 - 110 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS6490	3.357 ms	0 - 18 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	2.912 ms	0 - 72 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	1.134 ms	0 - 3 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® SA8775P	1.482 ms	0 - 74 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS9075	1.303 ms	0 - 18 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCM6690	9.846 ms	0 - 193 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	1.557 ms	0 - 112 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® SA7255P	2.912 ms	0 - 72 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® SA8295P	1.989 ms	0 - 70 MB	NPU
HRNetFace	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.578 ms	0 - 71 MB	NPU
HRNetFace	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.352 ms	0 - 75 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.