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 2.50, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.50, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.50 Download
QNN_DLC w8a8 Universal QAIRT 2.50 Download
TFLITE float Universal QAIRT 2.50 Download
TFLITE w8a8 Universal QAIRT 2.50 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® 8 Elite Gen 5 For Galaxy Mobile 1.298 ms 0 - 97 MB NPU
HRNetFace ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.61 ms 0 - 94 MB NPU
HRNetFace ONNX float Snapdragon® X2 Elite 1.509 ms 2 - 2 MB NPU
HRNetFace ONNX float Snapdragon® X Elite 2.913 ms 31 - 31 MB NPU
HRNetFace ONNX float Snapdragon® 8 Gen 3 Mobile 2.055 ms 0 - 151 MB NPU
HRNetFace ONNX float Snapdragon® 8 Gen 1 Mobile 4.314 ms 1 - 136 MB NPU
HRNetFace ONNX float Qualcomm® Dragonwing™ IQ-8275 4.804 ms 2 - 6 MB NPU
HRNetFace ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.79 ms 0 - 3 MB NPU
HRNetFace ONNX float Qualcomm® QCS8450 4.314 ms 1 - 136 MB NPU
HRNetFace ONNX float Qualcomm® Dragonwing™ IQ-9075 4.464 ms 2 - 5 MB NPU
HRNetFace ONNX float Qualcomm® Dragonwing™ IQ-X7181 2.913 ms 31 - 31 MB NPU
HRNetFace ONNX float Qualcomm® Dragonwing™ Q-8750 1.61 ms 0 - 94 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.594 ms 0 - 116 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.69 ms 0 - 113 MB NPU
HRNetFace ONNX w8a8 Snapdragon® X2 Elite 0.631 ms 1 - 1 MB NPU
HRNetFace ONNX w8a8 Snapdragon® X Elite 1.325 ms 15 - 15 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.877 ms 0 - 158 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.603 ms 0 - 161 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 3.87 ms 0 - 4 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 1.376 ms 0 - 4 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.331 ms 0 - 123 MB NPU
HRNetFace ONNX w8a8 Qualcomm® QCS8450 1.603 ms 0 - 161 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.511 ms 0 - 3 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.325 ms 15 - 15 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 10.052 ms 0 - 224 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.532 ms 0 - 118 MB NPU
HRNetFace ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.69 ms 0 - 113 MB NPU
HRNetFace ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.532 ms 0 - 118 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.383 ms 1 - 82 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.708 ms 0 - 78 MB NPU
HRNetFace QNN_DLC float Snapdragon® X2 Elite 1.877 ms 1 - 1 MB NPU
HRNetFace QNN_DLC float Snapdragon® X Elite 3.506 ms 1 - 1 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.229 ms 0 - 123 MB NPU
HRNetFace QNN_DLC float Snapdragon® 8 Gen 1 Mobile 5.238 ms 0 - 106 MB NPU
HRNetFace QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 4.915 ms 1 - 5 MB NPU
HRNetFace QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.154 ms 1 - 3 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8650P 5.105 ms 1 - 79 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8255P 5.105 ms 1 - 79 MB NPU
HRNetFace QNN_DLC float Qualcomm® QCS8450 5.238 ms 0 - 106 MB NPU
HRNetFace QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 4.715 ms 3 - 6 MB NPU
HRNetFace QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 3.506 ms 1 - 1 MB NPU
HRNetFace QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.708 ms 0 - 78 MB NPU
HRNetFace QNN_DLC float Qualcomm® SA8295P 5.261 ms 1 - 63 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.535 ms 0 - 74 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.668 ms 0 - 73 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® X2 Elite 0.821 ms 0 - 0 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® X Elite 1.543 ms 0 - 0 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.894 ms 0 - 109 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 1.682 ms 0 - 113 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 4.043 ms 2 - 5 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.389 ms 0 - 3 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.32 ms 0 - 2 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8650P 1.694 ms 0 - 72 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8255P 1.694 ms 0 - 72 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® QCS8450 1.682 ms 0 - 113 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.513 ms 0 - 3 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.543 ms 0 - 0 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 10.601 ms 0 - 191 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 1.643 ms 0 - 84 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.668 ms 0 - 73 MB NPU
HRNetFace QNN_DLC w8a8 Qualcomm® SA8295P 2.071 ms 0 - 73 MB NPU
HRNetFace QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.643 ms 0 - 84 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.387 ms 0 - 93 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.726 ms 0 - 94 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Gen 3 Mobile 2.238 ms 0 - 142 MB NPU
HRNetFace TFLITE float Snapdragon® 8 Gen 1 Mobile 5.175 ms 0 - 126 MB NPU
HRNetFace TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.922 ms 0 - 36 MB NPU
HRNetFace TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.142 ms 0 - 3 MB NPU
HRNetFace TFLITE float Qualcomm® SA8650P 5.144 ms 0 - 91 MB NPU
HRNetFace TFLITE float Qualcomm® SA8255P 5.144 ms 0 - 91 MB NPU
HRNetFace TFLITE float Qualcomm® QCS8450 5.175 ms 0 - 126 MB NPU
HRNetFace TFLITE float Qualcomm® Dragonwing™ IQ-9075 4.728 ms 0 - 35 MB NPU
HRNetFace TFLITE float Qualcomm® Dragonwing™ Q-8750 1.726 ms 0 - 94 MB NPU
HRNetFace TFLITE float Qualcomm® SA7255P 15.427 ms 1 - 92 MB NPU
HRNetFace TFLITE float Qualcomm® SA8295P 5.303 ms 1 - 74 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.467 ms 0 - 73 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.571 ms 0 - 71 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.727 ms 0 - 110 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 1.424 ms 0 - 116 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 3.779 ms 0 - 18 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 1.177 ms 0 - 19 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.091 ms 0 - 2 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8650P 1.48 ms 0 - 74 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8255P 1.48 ms 0 - 74 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® QCS8450 1.424 ms 0 - 116 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 1.295 ms 0 - 19 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 9.863 ms 0 - 188 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 1.38 ms 0 - 79 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.571 ms 0 - 71 MB NPU
HRNetFace TFLITE w8a8 Qualcomm® SA8295P 1.834 ms 0 - 72 MB NPU
HRNetFace TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.38 ms 0 - 79 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