Hugging Face's logo

qualcomm
/
Lightweight-Face-Detection

Object Detection
PyTorch
real_time
bu_iot
android
Model card Files
xet
 Community

Lightweight-Face-Detection: Optimized for Qualcomm Devices

A small and accurate model for detecting bounding boxes for faces in images. This model's architecture was developed by Qualcomm. The model was trained by Qualcomm on a proprietary dataset of faces, but can be used on any image.

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 w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a16_mixed_int16 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 w8a16 Universal QAIRT 2.43 Download
QNN_DLC w8a16_mixed_int16 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 Lightweight-Face-Detection 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 Lightweight-Face-Detection on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

  • Model checkpoint: qfd360_sl_model.pt
  • Inference latency: RealTime
  • Input resolution: 480x640
  • Number of parameters: 878K
  • Model size (float): 3.37 MB
  • Model size (w8a8): 965 KB
  • Model size (w8a16): 1.09 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Lightweight-Face-Detection ONNX float Snapdragon® 8 Elite Gen 5 Mobile 1.077 ms 0 - 148 MB NPU
Lightweight-Face-Detection ONNX float Snapdragon® X2 Elite 1.155 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX float Snapdragon® X Elite 2.187 ms 1 - 1 MB NPU
Lightweight-Face-Detection ONNX float Snapdragon® 8 Gen 3 Mobile 1.083 ms 0 - 160 MB NPU
Lightweight-Face-Detection ONNX float Qualcomm® QCS8550 (Proxy) 1.968 ms 1 - 3 MB NPU
Lightweight-Face-Detection ONNX float Qualcomm® QCS9075 2.487 ms 1 - 4 MB NPU
Lightweight-Face-Detection ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.893 ms 0 - 143 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.831 ms 0 - 146 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® X2 Elite 1.426 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® X Elite 1.969 ms 1 - 1 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.987 ms 0 - 156 MB NPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCS6490 88.417 ms 28 - 31 MB CPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCS8550 (Proxy) 1.75 ms 0 - 102 MB NPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCS9075 2.088 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCM6690 44.785 ms 27 - 35 MB CPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.851 ms 0 - 147 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 34.39 ms 28 - 36 MB CPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.84 ms 0 - 147 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® X2 Elite 0.907 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® X Elite 1.965 ms 1 - 1 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 1.015 ms 0 - 158 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCS6490 87.143 ms 32 - 35 MB CPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 1.719 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCS9075 2.114 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCM6690 44.914 ms 27 - 34 MB CPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.863 ms 0 - 147 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 34.365 ms 27 - 35 MB CPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.22 ms 0 - 145 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® X2 Elite 0.23 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® X Elite 0.583 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.312 ms 0 - 153 MB NPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCS6490 17.058 ms 13 - 17 MB CPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.454 ms 0 - 10 MB NPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCS9075 0.64 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCM6690 12.921 ms 13 - 22 MB CPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.252 ms 0 - 140 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 9.56 ms 13 - 22 MB CPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.082 ms 1 - 33 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® X2 Elite 1.395 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® X Elite 2.83 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.596 ms 0 - 42 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS8275 (Proxy) 6.687 ms 1 - 29 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS8550 (Proxy) 2.536 ms 1 - 3 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® SA8775P 3.239 ms 1 - 30 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS9075 3.703 ms 1 - 4 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS8450 (Proxy) 4.289 ms 0 - 43 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® SA7255P 6.687 ms 1 - 29 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® SA8295P 3.761 ms 1 - 26 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.221 ms 1 - 34 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.709 ms 1 - 142 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® X2 Elite 0.947 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® X Elite 1.959 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.963 ms 0 - 152 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS6490 6.539 ms 0 - 3 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 2.978 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 1.731 ms 1 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® SA8775P 1.951 ms 1 - 142 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS9075 2.17 ms 0 - 3 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCM6690 12.622 ms 1 - 140 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 2.89 ms 0 - 154 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® SA7255P 2.978 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® SA8295P 2.258 ms 0 - 137 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.773 ms 0 - 142 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 2.601 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.723 ms 1 - 143 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® X2 Elite 0.924 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® X Elite 1.991 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 0.968 ms 0 - 154 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8275 (Proxy) 3.181 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 1.769 ms 1 - 7 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® SA8775P 1.973 ms 1 - 142 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCS9075 2.31 ms 1 - 3 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCM6690 13.809 ms 1 - 141 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® SA7255P 3.181 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.829 ms 0 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 2.579 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.19 ms 0 - 27 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® X2 Elite 0.303 ms 0 - 0 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® X Elite 0.548 ms 0 - 0 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.287 ms 0 - 35 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS6490 1.287 ms 0 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 1.075 ms 0 - 25 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.414 ms 0 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® SA8775P 0.615 ms 0 - 26 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS9075 0.558 ms 0 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCM6690 2.816 ms 0 - 137 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.494 ms 0 - 36 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® SA7255P 1.075 ms 0 - 25 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® SA8295P 0.822 ms 0 - 23 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.23 ms 0 - 23 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.481 ms 0 - 138 MB NPU
Lightweight-Face-Detection TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.066 ms 0 - 34 MB NPU
Lightweight-Face-Detection TFLITE float Snapdragon® 8 Gen 3 Mobile 1.612 ms 0 - 43 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® QCS8275 (Proxy) 6.579 ms 0 - 29 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® QCS8550 (Proxy) 2.569 ms 0 - 6 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® SA8775P 3.233 ms 0 - 31 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® QCS9075 3.726 ms 0 - 5 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® QCS8450 (Proxy) 4.306 ms 0 - 44 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® SA7255P 6.579 ms 0 - 29 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® SA8295P 3.74 ms 0 - 27 MB NPU
Lightweight-Face-Detection TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.234 ms 0 - 34 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.189 ms 0 - 26 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.28 ms 35 - 69 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS6490 1.357 ms 0 - 3 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 1.117 ms 0 - 24 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.411 ms 0 - 1 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® SA8775P 0.625 ms 0 - 25 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS9075 0.597 ms 0 - 3 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCM6690 2.809 ms 0 - 137 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.51 ms 0 - 35 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® SA7255P 1.117 ms 0 - 24 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® SA8295P 0.844 ms 0 - 22 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.235 ms 0 - 28 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.482 ms 0 - 140 MB NPU

License

  • The license for the original implementation of Lightweight-Face-Detection can be found here.

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