insightface/RetinaFace

RetinaFace Face Detector

Introduction

RetinaFace is a practical single-stage face detector which is initially described in arXiv technical report

Data

1. Download our annotations (face bounding boxes & five facial landmarks) from baiducloud or dropbox

2. Download the WIDERFACE dataset.

3. Organise the dataset directory under insightface/RetinaFace/ as follows:

  data/retinaface/
    train/
      images/
      label.txt
    val/
      images/
      label.txt
    test/
      images/
      label.txt

Training

Please check train.py for training.

1. Copy rcnn/sample_config.py to rcnn/config.py
2. Download pretrained models and put them into model/. TODO_LINK
3. Start training with CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train.py --prefix ./model/retina --network resnet. You may want to check the resnet network configuration in rcnn/config.py before starting, like pretrained model path, anchor setting and learning rate policy etc..
4. Basically we have two predefined network settings called resnet(for medium and large size models) and mnet(for lightweight models).

Testing

Please check test.py for testing.

Models

Pretrained Model: RetinaFace-R50 (baiducloud or dropbox) is a medium size model with ResNet50 backbone. It can output face bounding boxes and five facial landmarks in a single forward pass. WiderFace validation mAP: Easy 96.5, Medium 95.6, Hard 90.4.

To avoid the confliction with the WiderFace Challenge (ICCV 2019), we postpone the release time of our best model.

References

@inproceedings{yang2016wider,
title = {WIDER FACE: A Face Detection Benchmark},
author = {Yang, Shuo and Luo, Ping and Loy, Chen Change and Tang, Xiaoou},
booktitle = {CVPR},
year = {2016}
}
  
@inproceedings{deng2019retinaface,
title={RetinaFace: Single-stage Dense Face Localisation in the Wild},
author={Deng, Jiankang and Guo, Jia and Yuxiang, Zhou and Jinke Yu and Irene Kotsia and Zafeiriou, Stefanos},
booktitle={arxiv},
year={2019}
}