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 2.45 Download
QNN_DLC w8a16 Universal QAIRT 2.45 Download
QNN_DLC w8a16_mixed_int16 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 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 1.088 ms 0 - 148 MB NPU
Lightweight-Face-Detection ONNX float Snapdragon® X2 Elite 1.157 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX float Snapdragon® X Elite 2.203 ms 1 - 1 MB NPU
Lightweight-Face-Detection ONNX float Snapdragon® 8 Gen 3 Mobile 1.087 ms 0 - 159 MB NPU
Lightweight-Face-Detection ONNX float Qualcomm® QCS8550 (Proxy) 1.959 ms 1 - 81 MB NPU
Lightweight-Face-Detection ONNX float Qualcomm® QCS9075 2.503 ms 1 - 4 MB NPU
Lightweight-Face-Detection ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.894 ms 0 - 140 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.832 ms 0 - 146 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® X2 Elite 0.905 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® X Elite 1.982 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 86.907 ms 28 - 31 MB CPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCS8550 (Proxy) 1.752 ms 0 - 107 MB NPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCS9075 2.112 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCM6690 44.575 ms 27 - 34 MB CPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.852 ms 0 - 142 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 34.328 ms 28 - 36 MB CPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.843 ms 0 - 148 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® X2 Elite 0.913 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® X Elite 1.956 ms 1 - 1 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 1.042 ms 0 - 158 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCS6490 88.508 ms 28 - 31 MB CPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 1.72 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCS9075 2.168 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCM6690 45.08 ms 27 - 34 MB CPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.867 ms 0 - 144 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 34.111 ms 29 - 37 MB CPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.219 ms 0 - 145 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® X2 Elite 0.222 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® X Elite 0.568 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.309 ms 0 - 152 MB NPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCS6490 16.999 ms 13 - 17 MB CPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.445 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCS9075 0.636 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCM6690 12.829 ms 12 - 20 MB CPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.251 ms 0 - 140 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 9.558 ms 12 - 20 MB CPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.075 ms 1 - 34 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® X2 Elite 1.351 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® X Elite 2.811 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.6 ms 0 - 42 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS8275 (Proxy) 6.676 ms 1 - 28 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS8550 (Proxy) 2.525 ms 1 - 3 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® SA8775P 3.245 ms 0 - 29 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS9075 3.707 ms 1 - 4 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS8450 (Proxy) 4.293 ms 1 - 43 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® SA7255P 6.676 ms 1 - 28 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® SA8295P 3.795 ms 1 - 27 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.217 ms 0 - 28 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.711 ms 1 - 143 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® X2 Elite 0.911 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® X Elite 1.988 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.959 ms 1 - 153 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS6490 6.504 ms 0 - 3 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 2.977 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 1.768 ms 0 - 3 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® SA8775P 1.88 ms 1 - 142 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS9075 2.207 ms 1 - 3 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCM6690 12.606 ms 1 - 144 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 2.877 ms 0 - 153 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® SA7255P 2.977 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® SA8295P 2.264 ms 0 - 137 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.771 ms 1 - 144 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 2.574 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.739 ms 1 - 143 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® X2 Elite 0.938 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® X Elite 2.044 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 1.019 ms 0 - 152 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8275 (Proxy) 3.285 ms 1 - 140 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 1.832 ms 1 - 73 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® SA8775P 2.069 ms 1 - 143 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCS9075 2.441 ms 1 - 3 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCM6690 13.572 ms 1 - 142 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® SA7255P 3.285 ms 1 - 140 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.817 ms 0 - 144 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 2.587 ms 1 - 140 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.191 ms 0 - 28 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® X2 Elite 0.302 ms 0 - 0 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® X Elite 0.528 ms 0 - 0 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.281 ms 0 - 35 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS6490 1.407 ms 0 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 1.082 ms 0 - 25 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.41 ms 0 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® SA8775P 0.598 ms 0 - 27 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS9075 0.552 ms 0 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCM6690 2.775 ms 0 - 138 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.498 ms 0 - 37 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® SA7255P 1.082 ms 0 - 25 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® SA8295P 0.843 ms 0 - 24 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.227 ms 0 - 30 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.478 ms 0 - 138 MB NPU
Lightweight-Face-Detection TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.067 ms 0 - 34 MB NPU
Lightweight-Face-Detection TFLITE float Snapdragon® 8 Gen 3 Mobile 1.631 ms 0 - 42 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® QCS8275 (Proxy) 6.6 ms 0 - 29 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® QCS8550 (Proxy) 2.551 ms 0 - 2 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® SA8775P 3.336 ms 0 - 31 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® QCS9075 3.705 ms 0 - 5 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® QCS8450 (Proxy) 4.292 ms 0 - 43 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® SA7255P 6.6 ms 0 - 29 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® SA8295P 3.795 ms 0 - 27 MB NPU
Lightweight-Face-Detection TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.238 ms 0 - 29 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.194 ms 0 - 27 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.279 ms 0 - 34 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS6490 1.363 ms 0 - 3 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 1.096 ms 0 - 24 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.412 ms 0 - 1 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® SA8775P 0.618 ms 0 - 26 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS9075 0.577 ms 0 - 3 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCM6690 2.807 ms 0 - 137 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.502 ms 0 - 35 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® SA7255P 1.096 ms 0 - 24 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® SA8295P 0.834 ms 0 - 22 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.238 ms 0 - 24 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.482 ms 0 - 137 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