Hugging Face's logo

qualcomm
/
HRNetFace

Object Detection
PyTorch
real_time
android
Model card Files
xet
 Community

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 1.25.0 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.25.0 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 1.327 ms 1 - 95 MB NPU
HRNetFace ONNX float Snapdragon® X2 Elite 1.536 ms 212 - 212 MB NPU
HRNetFace ONNX float Snapdragon® 8 Gen 3 Mobile 2.156 ms 0 - 152 MB NPU
HRNetFace ONNX float Qualcomm® QCS8550 (Proxy) 2.979 ms 0 - 41 MB NPU
HRNetFace ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.656 ms 0 - 94 MB NPU
HRNetFace ONNX float Qualcomm® QCS9075 4.755 ms 2 - 47 MB NPU
HRNetFace ONNX float Qualcomm® QCS8750 1.656 ms 0 - 94 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.577 ms 0 - 112 MB NPU
HRNetFace ONNX w8a8 Snapdragon® X2 Elite 0.655 ms 212 - 212 MB NPU
HRNetFace ONNX w8a8 Snapdragon® X Elite 1.346 ms 149 - 149 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.9 ms 0 - 161 MB NPU
HRNetFace ONNX w8a8 Qualcomm® QCS6490 91.765 ms 18 - 37 MB CPU
HRNetFace ONNX w8a8 Qualcomm® QCS8550 (Proxy) 1.364 ms 0 - 59 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 47.344 ms 17 - 37 MB CPU
HRNetFace ONNX w8a8 Qualcomm® QCM6690 50.035 ms 19 - 44 MB CPU
HRNetFace ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.698 ms 0 - 110 MB NPU
HRNetFace ONNX w8a8 Qualcomm® QCS9075 1.539 ms 0 - 45 MB NPU
HRNetFace ONNX w8a8 Qualcomm® QCS7790 47.344 ms 17 - 37 MB CPU
HRNetFace ONNX w8a8 Qualcomm® QCS8750 0.698 ms 0 - 110 MB NPU
HRNetFace ONNX w8a8 Qualcomm® QCS7181 1.346 ms 149 - 149 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.379 ms 1 - 80 MB NPU
HRNetFace QNN_DLC float Snapdragon® X2 Elite 1.918 ms 1 - 1 MB NPU
HRNetFace QNN_DLC float Snapdragon® X Elite 3.664 ms 1 - 1 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.337 ms 0 - 119 MB NPU
HRNetFace QNN_DLC float Qualcomm® QCS8275 15.433 ms 1 - 75 MB NPU
HRNetFace QNN_DLC float Qualcomm® QCS8550 (Proxy) 3.33 ms 0 - 12 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8775P 5.071 ms 1 - 79 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8650P 5.071 ms 1 - 79 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8255P 5.071 ms 1 - 79 MB NPU
HRNetFace QNN_DLC float Qualcomm® QCS8450 (Proxy) 5.49 ms 0 - 106 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8295P 5.636 ms 1 - 62 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.754 ms 0 - 78 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA7255P 15.433 ms 1 - 75 MB NPU
HRNetFace QNN_DLC float Qualcomm® QCS9075 5.021 ms 1 - 4 MB NPU
HRNetFace QNN_DLC float Qualcomm® QCS8750 1.754 ms 0 - 78 MB NPU
HRNetFace QNN_DLC float Qualcomm® QCS7181 3.664 ms 1 - 1 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.537 ms 0 - 74 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® X2 Elite 0.838 ms 0 - 0 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® X Elite 1.524 ms 0 - 0 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.897 ms 0 - 107 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS6490 3.829 ms 0 - 2 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS8275 3.276 ms 0 - 71 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 1.34 ms 0 - 2 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8775P 1.715 ms 0 - 72 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8650P 1.715 ms 0 - 72 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8255P 1.715 ms 0 - 72 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA7255P 3.276 ms 0 - 71 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.62 ms 0 - 79 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8295P 2.221 ms 0 - 69 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCM6690 10.507 ms 0 - 199 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.673 ms 0 - 69 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS9075 1.616 ms 0 - 2 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 1.854 ms 0 - 110 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS7790 1.62 ms 0 - 79 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS8750 0.673 ms 0 - 69 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS7181 1.524 ms 0 - 0 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.377 ms 0 - 96 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Gen 3 Mobile 2.336 ms 0 - 137 MB NPU
HRNetFace TFLITE float Qualcomm® QCS8275 15.48 ms 1 - 90 MB NPU
HRNetFace TFLITE float Qualcomm® QCS8550 (Proxy) 3.366 ms 0 - 5 MB NPU
HRNetFace TFLITE float Qualcomm® SA8775P 5.119 ms 0 - 93 MB NPU
HRNetFace TFLITE float Qualcomm® SA8650P 5.119 ms 0 - 93 MB NPU
HRNetFace TFLITE float Qualcomm® SA8255P 5.119 ms 0 - 93 MB NPU
HRNetFace TFLITE float Qualcomm® QCS8450 (Proxy) 5.494 ms 0 - 125 MB NPU
HRNetFace TFLITE float Qualcomm® SA8295P 5.659 ms 1 - 74 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.763 ms 0 - 94 MB NPU
HRNetFace TFLITE float Qualcomm® SA7255P 15.48 ms 1 - 90 MB NPU
HRNetFace TFLITE float Qualcomm® QCS9075 5.044 ms 0 - 35 MB NPU
HRNetFace TFLITE float Qualcomm® QCS8750 1.763 ms 0 - 94 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.46 ms 0 - 75 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.737 ms 0 - 113 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS6490 3.22 ms 0 - 18 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS8275 2.896 ms 0 - 72 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 1.124 ms 0 - 12 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8775P 1.481 ms 0 - 74 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8650P 1.481 ms 0 - 74 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8255P 1.481 ms 0 - 74 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA7255P 2.896 ms 0 - 72 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.363 ms 0 - 75 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8295P 1.994 ms 0 - 70 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCM6690 9.837 ms 0 - 193 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.578 ms 0 - 68 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS9075 1.315 ms 0 - 18 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 1.571 ms 0 - 113 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS7790 1.363 ms 0 - 75 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS8750 0.578 ms 0 - 68 MB NPU

License

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

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Object Detection
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/HRNetFace