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 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.27.1 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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
HRNetFace ONNX float Snapdragon® X2 Elite 1.546 ms 2 - 2 MB NPU
HRNetFace ONNX float Snapdragon® X Elite 3.16 ms 31 - 31 MB NPU
HRNetFace ONNX float Snapdragon® 8 Gen 3 Mobile 2.145 ms 0 - 149 MB NPU
HRNetFace ONNX float Snapdragon® 8 Gen 1 Mobile 4.525 ms 1 - 135 MB NPU
HRNetFace ONNX float Qualcomm® Dragonwing™ IQ-8275 4.892 ms 2 - 5 MB NPU
HRNetFace ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.989 ms 0 - 34 MB NPU
HRNetFace ONNX float Qualcomm® QCS8450 4.525 ms 1 - 135 MB NPU
HRNetFace ONNX float Qualcomm® Dragonwing™ IQ-9075 4.611 ms 2 - 4 MB NPU
HRNetFace ONNX float Qualcomm® Dragonwing™ IQ-X7181 3.16 ms 31 - 31 MB NPU
HRNetFace ONNX float Qualcomm® Dragonwing™ Q-8750 1.651 ms 0 - 95 MB NPU
HRNetFace ONNX float Snapdragon® 8 Elite Mobile 1.651 ms 0 - 95 MB NPU
HRNetFace ONNX float Snapdragon® 8 Elite Gen 5 Mobile 1.355 ms 0 - 96 MB NPU
HRNetFace ONNX w8a8 Snapdragon® X2 Elite 0.661 ms 1 - 1 MB NPU
HRNetFace ONNX w8a8 Snapdragon® X Elite 1.323 ms 15 - 15 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.879 ms 0 - 153 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.746 ms 0 - 156 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 5.146 ms 0 - 3 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 1.398 ms 0 - 4 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.287 ms 0 - 18 MB NPU
HRNetFace ONNX w8a8 Qualcomm® QCS8450 1.746 ms 0 - 156 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.504 ms 0 - 3 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.323 ms 15 - 15 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 10.044 ms 0 - 233 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.582 ms 0 - 114 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.704 ms 0 - 110 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Elite Mobile 0.704 ms 0 - 110 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.597 ms 0 - 111 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.582 ms 0 - 114 MB NPU
HRNetFace QNN_DLC float Snapdragon® X2 Elite 1.979 ms 1 - 1 MB NPU
HRNetFace QNN_DLC float Snapdragon® X Elite 3.677 ms 1 - 1 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.328 ms 0 - 120 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Gen 1 Mobile 5.477 ms 0 - 105 MB NPU
HRNetFace QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 4.963 ms 1 - 4 MB NPU
HRNetFace QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 15.421 ms 1 - 76 MB NPU
HRNetFace QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.287 ms 1 - 2 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8775P 5.094 ms 1 - 79 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8650P 5.094 ms 1 - 79 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8255P 5.094 ms 1 - 79 MB NPU
HRNetFace QNN_DLC float Qualcomm® QCS8450 5.477 ms 0 - 105 MB NPU
HRNetFace QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 5.337 ms 1 - 4 MB NPU
HRNetFace QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 3.677 ms 1 - 1 MB NPU
HRNetFace QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.759 ms 1 - 78 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA7255P 15.421 ms 1 - 76 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8295P 5.647 ms 1 - 62 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Elite Mobile 1.759 ms 1 - 78 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.412 ms 1 - 80 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® X2 Elite 0.849 ms 0 - 0 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® X Elite 1.557 ms 0 - 0 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.919 ms 0 - 106 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 1.849 ms 0 - 109 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 5.521 ms 2 - 4 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.395 ms 0 - 3 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 3.256 ms 0 - 70 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.326 ms 0 - 2 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8775P 1.708 ms 0 - 72 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8650P 1.708 ms 0 - 72 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8255P 1.708 ms 0 - 72 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS8450 1.849 ms 0 - 109 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.532 ms 0 - 2 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.557 ms 0 - 0 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 10.628 ms 0 - 200 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 1.652 ms 0 - 79 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.675 ms 0 - 68 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA7255P 3.256 ms 0 - 70 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8295P 2.195 ms 0 - 69 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.675 ms 0 - 68 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.541 ms 0 - 72 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.652 ms 0 - 79 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Gen 3 Mobile 2.342 ms 0 - 140 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Gen 1 Mobile 5.483 ms 0 - 127 MB NPU
HRNetFace TFLITE float Qualcomm® Dragonwing™ IQ-8275 5.013 ms 0 - 35 MB NPU
HRNetFace TFLITE float Qualcomm® Dragonwing™ IQ-8275 15.483 ms 1 - 90 MB NPU
HRNetFace TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.315 ms 0 - 3 MB NPU
HRNetFace TFLITE float Qualcomm® SA8775P 5.157 ms 0 - 92 MB NPU
HRNetFace TFLITE float Qualcomm® SA8650P 5.157 ms 0 - 92 MB NPU
HRNetFace TFLITE float Qualcomm® SA8255P 5.157 ms 0 - 92 MB NPU
HRNetFace TFLITE float Qualcomm® QCS8450 5.483 ms 0 - 127 MB NPU
HRNetFace TFLITE float Qualcomm® Dragonwing™ IQ-9075 4.867 ms 0 - 35 MB NPU
HRNetFace TFLITE float Qualcomm® Dragonwing™ Q-8750 1.759 ms 0 - 95 MB NPU
HRNetFace TFLITE float Qualcomm® SA7255P 15.483 ms 1 - 90 MB NPU
HRNetFace TFLITE float Qualcomm® SA8295P 5.68 ms 1 - 74 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Elite Mobile 1.759 ms 0 - 95 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.41 ms 0 - 90 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.716 ms 0 - 115 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 1.551 ms 0 - 112 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 5.302 ms 0 - 18 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 1.204 ms 0 - 18 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 2.89 ms 0 - 72 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.099 ms 0 - 20 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8775P 1.5 ms 0 - 74 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8650P 1.5 ms 0 - 74 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8255P 1.5 ms 0 - 74 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS8450 1.551 ms 0 - 112 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 1.298 ms 0 - 18 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 9.852 ms 0 - 192 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 1.351 ms 0 - 75 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.587 ms 0 - 71 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA7255P 2.89 ms 0 - 72 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8295P 1.981 ms 0 - 69 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.587 ms 0 - 71 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.474 ms 0 - 71 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.351 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