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 2.37, ONNX Runtime 1.23.0 Download
ONNX w8a16 Universal QAIRT 2.37, ONNX Runtime 1.23.0 Download
ONNX w8a16_mixed_int16 Universal QAIRT 2.37, ONNX Runtime 1.23.0 Download
ONNX w8a8 Universal QAIRT 2.37, ONNX Runtime 1.23.0 Download
QNN_DLC float Universal QAIRT 2.42 Download
QNN_DLC w8a16 Universal QAIRT 2.42 Download
QNN_DLC w8a16_mixed_int16 Universal QAIRT 2.42 Download
QNN_DLC w8a8 Universal QAIRT 2.42 Download
TFLITE float Universal QAIRT 2.42, TFLite 2.17.0 Download
TFLITE w8a8 Universal QAIRT 2.42, TFLite 2.17.0 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® X Elite 2.462 ms 1 - 1 MB NPU
Lightweight-Face-Detection ONNX float Snapdragon® 8 Gen 3 Mobile 1.408 ms 0 - 112 MB NPU
Lightweight-Face-Detection ONNX float Qualcomm® QCS8550 (Proxy) 2.706 ms 0 - 7 MB NPU
Lightweight-Face-Detection ONNX float Qualcomm® QCS9075 2.694 ms 1 - 4 MB NPU
Lightweight-Face-Detection ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.217 ms 0 - 96 MB NPU
Lightweight-Face-Detection ONNX float Snapdragon® 8 Elite Gen 5 Mobile 1.256 ms 0 - 103 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® X Elite 1.944 ms 1 - 1 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1.189 ms 0 - 114 MB NPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCS6490 87.108 ms 29 - 32 MB CPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCS8550 (Proxy) 1.935 ms 0 - 122 MB NPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCS9075 2.412 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCM6690 43.818 ms 29 - 36 MB CPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.947 ms 0 - 101 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 33.473 ms 29 - 36 MB CPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.919 ms 0 - 102 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® X Elite 2.027 ms 1 - 1 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 1.248 ms 0 - 111 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCS6490 91.198 ms 28 - 32 MB CPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 2.063 ms 0 - 8 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCS9075 2.288 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCM6690 43.997 ms 28 - 35 MB CPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.988 ms 0 - 103 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 33.242 ms 30 - 37 MB CPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.93 ms 0 - 101 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® X Elite 0.554 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.474 ms 0 - 107 MB NPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCS6490 16.911 ms 12 - 17 MB CPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.623 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCS9075 0.838 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCM6690 12.739 ms 13 - 21 MB CPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.354 ms 0 - 100 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 9.371 ms 12 - 20 MB CPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.331 ms 0 - 100 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® X Elite 2.872 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.621 ms 0 - 42 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS8275 (Proxy) 6.779 ms 1 - 29 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS8550 (Proxy) 2.602 ms 1 - 24 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® SA8775P 14.285 ms 1 - 29 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS9075 3.692 ms 1 - 4 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS8450 (Proxy) 4.31 ms 0 - 43 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® SA7255P 6.779 ms 1 - 29 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® SA8295P 3.79 ms 0 - 25 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.218 ms 1 - 34 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.1 ms 1 - 34 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® X Elite 1.909 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.939 ms 0 - 155 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS6490 6.589 ms 2 - 5 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 2.989 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 1.675 ms 1 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® SA8775P 1.941 ms 1 - 141 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS9075 2.171 ms 2 - 5 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCM6690 12.4 ms 1 - 140 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 2.894 ms 1 - 155 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® SA7255P 2.989 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® SA8295P 2.34 ms 1 - 137 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.774 ms 0 - 143 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 2.605 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.713 ms 1 - 143 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® X Elite 1.979 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 0.959 ms 0 - 153 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8275 (Proxy) 3.246 ms 1 - 140 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 1.739 ms 1 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® SA8775P 1.957 ms 0 - 142 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCS9075 2.37 ms 0 - 3 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCM6690 14.536 ms 1 - 140 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® SA7255P 3.246 ms 1 - 140 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.815 ms 0 - 143 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 2.629 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.756 ms 1 - 143 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® X Elite 0.536 ms 0 - 0 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.276 ms 0 - 34 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS6490 1.41 ms 2 - 4 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 1.081 ms 0 - 26 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 0.614 ms 0 - 26 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS9075 0.553 ms 0 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCM6690 2.813 ms 0 - 141 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.499 ms 0 - 36 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® SA7255P 1.081 ms 0 - 26 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® SA8295P 0.823 ms 0 - 23 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.23 ms 0 - 28 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.487 ms 0 - 138 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.198 ms 0 - 27 MB NPU
Lightweight-Face-Detection TFLITE float Snapdragon® 8 Gen 3 Mobile 1.633 ms 0 - 43 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® QCS8275 (Proxy) 6.711 ms 0 - 29 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® QCS8550 (Proxy) 2.607 ms 0 - 59 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® SA8775P 3.346 ms 0 - 31 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® QCS9075 3.709 ms 0 - 5 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® QCS8450 (Proxy) 4.285 ms 0 - 43 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® SA7255P 6.711 ms 0 - 29 MB NPU
Lightweight-Face-Detection TFLITE float Qualcomm® SA8295P 3.783 ms 0 - 27 MB NPU
Lightweight-Face-Detection TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.231 ms 0 - 34 MB NPU
Lightweight-Face-Detection TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.11 ms 0 - 34 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.284 ms 0 - 34 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS6490 1.412 ms 0 - 3 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 1.126 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 0.623 ms 0 - 26 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS9075 0.574 ms 0 - 3 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCM6690 2.799 ms 0 - 136 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.507 ms 0 - 35 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® SA7255P 1.126 ms 0 - 24 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® SA8295P 0.829 ms 0 - 22 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.235 ms 0 - 23 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.496 ms 0 - 136 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.197 ms 0 - 27 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