This repository is cloned from Tencent/FaceDetection-DSFD and modified for research, compatibility, functionality and convenience.
In this repo, we propose a novel face detection network, named DSFD, with superior performance over the state-of-the-art face detectors. You can use the code to evaluate our DSFD for face detection.
For more details, please refer to our paper DSFD: Dual Shot Face Detector! or poster slide!
Our DSFD face detector achieves state-of-the-art performance on WIDER FACE and FDDB benchmark.
Backbone | Easy | Medium | Hard | E2E latency (s) | Download |
---|---|---|---|---|---|
ResNet-152 | 0.967 | 0.952 | 0.905 | 6.26 | here |
Easy, Medium and Hard denote AP on WIDER FACE validation set Easy, Medium and Hard, respectively.
E2E latency denotes an end-to-end latency (= preprocess + network + TTA + postprocess).
Latency is measured with batch size 1 on RTX 2080Ti GPU and Threadripper 2950X CPU.
Confidence thresholds were set to 0.01 for both AP and latency benchmark.
cudatoolkit==10.2
cudnn==7.6
python==3.6
torch==1.4.0
torchvision==0.5.0
> git clone https://github.com/swoook/dsfd.git
> cd ${DSFD_DIR}/dsfd
If you find DSFD useful in your research, please consider citing:
@inproceedings{li2018dsfd,
title={DSFD: Dual Shot Face Detector},
author={Li, Jian and Wang, Yabiao and Wang, Changan and Tai, Ying and Qian, Jianjun and Yang, Jian and Wang, Chengjie and Li, Jilin and Huang, Feiyue},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
year={2019}
}
For any question, please file an issue or contact
Jian Li: swordli@tencent.com