You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Sirius Demon 6c6b15867b
1 year ago
caffenet initial commit 2 years ago
imgs initial commit 2 years ago
pcn update location 1 year ago
result regenerate image 2 years ago
.gitignore initial commit 2 years ago
LICENSE Initial commit 2 years ago Update 1 year ago Update 1 year ago pcn as a package! and crop face is implemented 1 year ago pcn as a package! and crop face is implemented 1 year ago update webcam demo! 1 year ago

PCN in Pytorch


Progressive Calibration Networks (PCN) is an accurate rotation-invariant face detector running at real-time speed on CPU. This is an implementation for PCN.

This is a pytorch implementation version of the original repo

Getting Started

A separate Python environment is recommended.

  • Python3.5+ (Python3.5, Python3.6 are tested)
  • Pytorch == 1.0
  • opencv4 (opencv3.4.5 is tested also)
  • numpy

install dependences using pip

pip3 install numpy opencv-python
pip3 install
pip3 install torchvision (optional)

or install using conda

conda install opencv numpy
conda install pytorch-cpu torchvision-cpu -c pytorch


cd pytorch-PCN
python path/to/image 

or use webcam demo



cd pytorch-PCN && pip install .


More results can be found in result directory, or you can run the script to generate them.

There is still one image failed. Pull requests to fix it is welcome.


This code is distributed under the BSD 2-Clause license.

Citing & Thanks

    Author = {Xuepeng Shi and Shiguang Shan and Meina Kan and Shuzhe Wu and Xilin Chen},
    Title = {Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks},
    Booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    Year = {2018}


For anyone who hear, see, think about or use this repo, I hope them gain temporary happiness and everlasting happiness