实时人脸检测centerface

# the real-time face detection Centerface

unofficial version of centerface, which achieves the best balance between speed and accuracy. Centerface is a practical anchor-free face detection and alignment method for edge devices.

The project provides training scripts, training data sets, and pre-training models to facilitate users to reproduce the results. Finally, thank the centerface's author for the training advice.

performance results on the validation set of WIDER_FACE

use the same train dataset without additional data

Requirements

use pytorch, you can use pip or conda to install the requirements

# for pip
cd $project
pip install -r requirements.txt

# for conda
conda env create -f enviroment.yaml

Test

1. download the pretrained model from Baidu password: ypbi

2. download the validation set of WIDER_FACE password: ypbi

3. test on the validation set

cd $project/src
source activate torch110
python test_wider_face.py

4. calculate the accuracy

cd $project/evaluate
python3 setup.py build_ext --inplace
python evaluation.py --pred {the result folder}
    
>>>
Easy   Val AP: 0.9257383419951156
Medium Val AP: 0.9131308732465665
Hard   Val AP: 0.7717305552550734

5. example

   
   
   在这里插入图片描述
6. vedio

[video(video-h0NmS5hq-1582250918283)(type-bilibili)(url-https://player.bilibili.com/player.html?aid=88180133)(image-https://ss.csdn.net/p?http://i0.hdslb.com/bfs/archive/4972610bf25f6d7d0e6c9156e02ef18ff11b72a1.jpg)(title-TensorRT centerface人脸+关键点检测做到50fps)]

7. face recognition

[video(video-w5il8NlR-1582634924047)(type-bilibili)(url-https://player.bilibili.com/player.html?aid=91632471)(image-https://ss.csdn.net/p?http://i2.hdslb.com/bfs/archive/1c03d109a1a373184ea11fffdc557a7f89116d96.jpg)(title-[人脸识别]高精度centerface)]

Train

the backbone use mobilev2 as the same with the original paper
The annotation file is in coco format. the annotation file and train data can download for Baidu password: ypbi
train

cd $project/src/tools
source activate torch110
python main.py

Train on your own data

follow the CenterNet

TO DO

• use more powerful and small backbone
• use other FPN tricks

reference

borrow code from CenterNet

CenterNet
CenterMulti
Star-Clouds/CenterFace

Code

https://github.com/chenjun2hao/CenterFace.pytorch