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 1.24.3 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 1.328 ms 1 - 99 MB NPU
HRNetFace ONNX float Snapdragon® 8 Elite Mobile 1.651 ms 0 - 95 MB NPU
HRNetFace ONNX float Snapdragon® X2 Elite 1.533 ms 31 - 31 MB NPU
HRNetFace ONNX float Snapdragon® X Elite 3.359 ms 30 - 30 MB NPU
HRNetFace ONNX float Snapdragon® X Elite 3.359 ms 30 - 30 MB NPU
HRNetFace ONNX float Snapdragon® 8 Gen 3 Mobile 2.147 ms 0 - 149 MB NPU
HRNetFace ONNX float Qualcomm® QCS8550 (Proxy) 2.981 ms 0 - 37 MB NPU
HRNetFace ONNX float Qualcomm® QCS9075 4.743 ms 2 - 4 MB NPU
HRNetFace ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.651 ms 0 - 95 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.589 ms 0 - 106 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Elite Mobile 0.695 ms 0 - 105 MB NPU
HRNetFace ONNX w8a8 Snapdragon® X2 Elite 0.657 ms 15 - 15 MB NPU
HRNetFace ONNX w8a8 Snapdragon® X Elite 1.535 ms 15 - 15 MB NPU
HRNetFace ONNX w8a8 Snapdragon® X Elite 1.535 ms 15 - 15 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.91 ms 0 - 154 MB NPU
HRNetFace ONNX w8a8 Qualcomm® QCS6490 91.191 ms 17 - 36 MB CPU
HRNetFace ONNX w8a8 Qualcomm® QCS8550 (Proxy) 1.367 ms 0 - 21 MB NPU
HRNetFace ONNX w8a8 Qualcomm® QCS9075 1.537 ms 0 - 3 MB NPU
HRNetFace ONNX w8a8 Qualcomm® QCM6690 49.667 ms 19 - 39 MB CPU
HRNetFace ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.695 ms 0 - 105 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 46.653 ms 17 - 37 MB CPU
HRNetFace ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 46.653 ms 17 - 37 MB CPU
HRNetFace QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.378 ms 1 - 81 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Elite Mobile 1.753 ms 0 - 79 MB NPU
HRNetFace QNN_DLC float Snapdragon® X2 Elite 1.917 ms 1 - 1 MB NPU
HRNetFace QNN_DLC float Snapdragon® X Elite 3.699 ms 1 - 1 MB NPU
HRNetFace QNN_DLC float Snapdragon® X Elite 3.699 ms 1 - 1 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.332 ms 0 - 123 MB NPU
HRNetFace QNN_DLC float Qualcomm® QCS8275 (Proxy) 15.425 ms 1 - 75 MB NPU
HRNetFace QNN_DLC float Qualcomm® QCS8550 (Proxy) 3.324 ms 1 - 143 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8775P 5.087 ms 1 - 79 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8775P 5.087 ms 1 - 79 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8775P 5.087 ms 1 - 79 MB NPU
HRNetFace QNN_DLC float Qualcomm® QCS9075 5.027 ms 1 - 4 MB NPU
HRNetFace QNN_DLC float Qualcomm® QCS8450 (Proxy) 5.48 ms 0 - 104 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA7255P 15.425 ms 1 - 75 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8295P 5.67 ms 1 - 62 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.753 ms 0 - 79 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.536 ms 0 - 74 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.679 ms 0 - 74 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® X2 Elite 0.868 ms 0 - 0 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® X Elite 1.545 ms 0 - 0 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® X Elite 1.545 ms 0 - 0 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.912 ms 0 - 108 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS6490 3.817 ms 0 - 2 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 3.253 ms 0 - 71 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 1.322 ms 0 - 2 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8775P 1.709 ms 0 - 74 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8775P 1.709 ms 0 - 74 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8775P 1.709 ms 0 - 74 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS9075 1.616 ms 0 - 2 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCM6690 10.61 ms 0 - 200 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 1.845 ms 0 - 109 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA7255P 3.253 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 0.679 ms 0 - 74 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.625 ms 0 - 80 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.625 ms 0 - 80 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.377 ms 0 - 96 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Elite Mobile 1.759 ms 0 - 94 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Gen 3 Mobile 2.333 ms 0 - 138 MB NPU
HRNetFace TFLITE float Qualcomm® QCS8275 (Proxy) 15.48 ms 0 - 92 MB NPU
HRNetFace TFLITE float Qualcomm® QCS8550 (Proxy) 3.315 ms 0 - 2 MB NPU
HRNetFace TFLITE float Qualcomm® SA8775P 5.127 ms 1 - 92 MB NPU
HRNetFace TFLITE float Qualcomm® SA8775P 5.127 ms 1 - 92 MB NPU
HRNetFace TFLITE float Qualcomm® SA8775P 5.127 ms 1 - 92 MB NPU
HRNetFace TFLITE float Qualcomm® QCS9075 5.057 ms 0 - 35 MB NPU
HRNetFace TFLITE float Qualcomm® QCS8450 (Proxy) 5.498 ms 0 - 125 MB NPU
HRNetFace TFLITE float Qualcomm® SA7255P 15.48 ms 0 - 92 MB NPU
HRNetFace TFLITE float Qualcomm® SA8295P 5.669 ms 0 - 74 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.759 ms 0 - 94 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.456 ms 0 - 75 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.58 ms 0 - 72 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.731 ms 0 - 113 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS6490 3.35 ms 0 - 18 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 2.888 ms 0 - 72 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 1.097 ms 0 - 2 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8775P 1.499 ms 0 - 75 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8775P 1.499 ms 0 - 75 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8775P 1.499 ms 0 - 75 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS9075 1.305 ms 0 - 18 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCM6690 9.847 ms 0 - 192 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 1.563 ms 0 - 112 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA7255P 2.888 ms 0 - 72 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8295P 1.985 ms 0 - 69 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.58 ms 0 - 72 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.357 ms 0 - 75 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.357 ms 0 - 75 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