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 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.19.1	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	1.327 ms	1 - 98 MB	NPU
HRNetFace	ONNX	float	Snapdragon® X2 Elite	1.547 ms	31 - 31 MB	NPU
HRNetFace	ONNX	float	Snapdragon® X Elite	3.333 ms	30 - 30 MB	NPU
HRNetFace	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.148 ms	0 - 150 MB	NPU
HRNetFace	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.973 ms	0 - 37 MB	NPU
HRNetFace	ONNX	float	Qualcomm® QCS9075	4.773 ms	2 - 4 MB	NPU
HRNetFace	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.649 ms	0 - 96 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.59 ms	0 - 105 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® X2 Elite	0.658 ms	15 - 15 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® X Elite	1.551 ms	15 - 15 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.913 ms	0 - 152 MB	NPU
HRNetFace	ONNX	w8a8	Qualcomm® QCS6490	93.08 ms	18 - 36 MB	CPU
HRNetFace	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	1.304 ms	0 - 37 MB	NPU
HRNetFace	ONNX	w8a8	Qualcomm® QCS9075	1.536 ms	0 - 3 MB	NPU
HRNetFace	ONNX	w8a8	Qualcomm® QCM6690	49.768 ms	20 - 39 MB	CPU
HRNetFace	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.695 ms	0 - 96 MB	NPU
HRNetFace	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	47.013 ms	19 - 37 MB	CPU
HRNetFace	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.37 ms	1 - 83 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® X2 Elite	1.905 ms	1 - 1 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® X Elite	3.701 ms	1 - 1 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.336 ms	0 - 124 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	15.46 ms	1 - 77 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.329 ms	1 - 3 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® SA8775P	5.14 ms	1 - 80 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® QCS9075	5.028 ms	1 - 4 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	5.424 ms	0 - 107 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® SA7255P	15.46 ms	1 - 77 MB	NPU
HRNetFace	QNN_DLC	float	Qualcomm® SA8295P	5.619 ms	0 - 61 MB	NPU
HRNetFace	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.747 ms	1 - 80 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.539 ms	0 - 72 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.849 ms	0 - 0 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® X Elite	1.569 ms	0 - 0 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.921 ms	0 - 108 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS6490	3.759 ms	0 - 2 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	3.227 ms	0 - 70 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	1.326 ms	0 - 15 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® SA8775P	1.701 ms	0 - 72 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS9075	1.622 ms	2 - 4 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCM6690	10.477 ms	0 - 197 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	1.878 ms	0 - 110 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® SA7255P	3.227 ms	0 - 70 MB	NPU
HRNetFace	QNN_DLC	w8a8	Qualcomm® SA8295P	2.2 ms	0 - 68 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.665 ms	0 - 71 MB	NPU
HRNetFace	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.637 ms	0 - 79 MB	NPU
HRNetFace	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.384 ms	0 - 100 MB	NPU
HRNetFace	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.335 ms	0 - 144 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® QCS8275 (Proxy)	15.446 ms	1 - 93 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.357 ms	0 - 2 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® SA8775P	5.188 ms	0 - 94 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® QCS9075	5.051 ms	0 - 35 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® QCS8450 (Proxy)	5.45 ms	0 - 127 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® SA7255P	15.446 ms	1 - 93 MB	NPU
HRNetFace	TFLITE	float	Qualcomm® SA8295P	5.657 ms	1 - 76 MB	NPU
HRNetFace	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.758 ms	0 - 90 MB	NPU
HRNetFace	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.464 ms	0 - 73 MB	NPU
HRNetFace	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.766 ms	0 - 114 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS6490	3.508 ms	0 - 18 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	2.91 ms	0 - 71 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	1.1 ms	0 - 3 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® SA8775P	1.487 ms	0 - 73 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS9075	1.339 ms	0 - 18 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCM6690	9.784 ms	0 - 197 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	1.516 ms	0 - 111 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® SA7255P	2.91 ms	0 - 71 MB	NPU
HRNetFace	TFLITE	w8a8	Qualcomm® SA8295P	1.963 ms	0 - 68 MB	NPU
HRNetFace	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.573 ms	0 - 73 MB	NPU
HRNetFace	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.354 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.