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 0.907 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 0.984 ms 0 - 156 MB NPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCS6490 87.283 ms 30 - 33 MB CPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCS8550 (Proxy) 1.751 ms 0 - 9 MB NPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCS9075 2.089 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a16 Qualcomm® QCM6690 44.747 ms 28 - 35 MB CPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.852 ms 0 - 145 MB NPU
Lightweight-Face-Detection ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 34.204 ms 28 - 36 MB CPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.841 ms 0 - 146 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® X2 Elite 0.912 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® X Elite 1.945 ms 1 - 1 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 1.001 ms 0 - 157 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCS6490 87.945 ms 29 - 31 MB CPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 1.718 ms 0 - 32 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCS9075 2.169 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Qualcomm® QCM6690 44.977 ms 27 - 34 MB CPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.86 ms 0 - 141 MB NPU
Lightweight-Face-Detection ONNX w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 34.002 ms 28 - 35 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 0.221 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® X Elite 0.573 ms 0 - 0 MB NPU
Lightweight-Face-Detection ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.304 ms 0 - 153 MB NPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCS6490 17.164 ms 12 - 17 MB CPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.45 ms 0 - 10 MB NPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCS9075 0.66 ms 0 - 3 MB NPU
Lightweight-Face-Detection ONNX w8a8 Qualcomm® QCM6690 12.82 ms 13 - 21 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 9.583 ms 12 - 20 MB CPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.079 ms 1 - 34 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® X2 Elite 1.367 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® X Elite 2.787 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.599 ms 0 - 41 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS8275 (Proxy) 6.694 ms 1 - 27 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 3.239 ms 1 - 31 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS9075 3.693 ms 1 - 4 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® QCS8450 (Proxy) 4.281 ms 0 - 42 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® SA7255P 6.694 ms 1 - 27 MB NPU
Lightweight-Face-Detection QNN_DLC float Qualcomm® SA8295P 3.797 ms 0 - 26 MB NPU
Lightweight-Face-Detection QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.217 ms 1 - 30 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.722 ms 1 - 143 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® X2 Elite 0.928 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® X Elite 1.973 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.956 ms 0 - 152 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS6490 6.584 ms 1 - 3 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 2.949 ms 0 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 1.759 ms 1 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® SA8775P 1.898 ms 1 - 142 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS9075 2.207 ms 3 - 5 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCM6690 12.749 ms 1 - 141 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 2.88 ms 0 - 153 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® SA7255P 2.949 ms 0 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Qualcomm® SA8295P 2.275 ms 1 - 138 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.771 ms 0 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 2.58 ms 0 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.749 ms 1 - 143 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® X2 Elite 0.952 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® X Elite 1.967 ms 1 - 1 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 0.946 ms 0 - 156 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8275 (Proxy) 3.184 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 1.76 ms 1 - 96 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® SA8775P 1.929 ms 0 - 142 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCS9075 2.322 ms 1 - 3 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® QCM6690 13.493 ms 1 - 142 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Qualcomm® SA7255P 3.184 ms 1 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.796 ms 1 - 144 MB NPU
Lightweight-Face-Detection QNN_DLC w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 2.551 ms 1 - 140 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.193 ms 0 - 27 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® X2 Elite 0.308 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 0.282 ms 0 - 35 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS6490 1.41 ms 0 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 1.089 ms 0 - 25 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.402 ms 0 - 2 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® SA8775P 0.6 ms 0 - 28 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS9075 0.555 ms 2 - 4 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCM6690 2.815 ms 0 - 139 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.495 ms 0 - 37 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® SA7255P 1.089 ms 0 - 25 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Qualcomm® SA8295P 0.83 ms 0 - 24 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.225 ms 0 - 25 MB NPU
Lightweight-Face-Detection QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.478 ms 0 - 137 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 0.192 ms 0 - 27 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.286 ms 0 - 34 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS6490 1.335 ms 0 - 3 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 1.108 ms 0 - 24 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.412 ms 0 - 66 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® SA8775P 0.626 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 2.812 ms 0 - 137 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.506 ms 0 - 36 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® SA7255P 1.108 ms 0 - 24 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Qualcomm® SA8295P 0.842 ms 0 - 22 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.234 ms 0 - 25 MB NPU
Lightweight-Face-Detection TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.483 ms 0 - 136 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