Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Appearance settings

bartolootrit/Retinaface_Mobilenet_Pytorch

Open more actions menu
 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RetinaFace in PyTorch

A PyTorch implementation of RetinaFace: Single-stage Dense Face Localisation in the Wild. The official code in Mxnet can be found here.

TODO

[ ] Move to detectron2

WiderFace Val Performance in single scale When using Mobilenet0.25 as backbone net.

Style easy medium hard
Mxnet(Single Scale 2150) 88.72% 86.97% 79.19%
Mxnet(Original Scale) 89.58% 87.11% 69.12%
Pytorch(Same as Mxnet 2150) 91.795% 90.49% 85.55%
Pytorch(Original Scale) 92.65% 90.91% 80.23%

Dependencies

  • pytorch == 1.3.1
  • torchvision == 0.4.0
  • python == 3.7

Installation

cd libs/DCNv2
./make.sh

Run Demo

python3 demo.py

About

Face Detection Based on Detectron2

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 43.4%
  • Cuda 41.1%
  • C++ 11.3%
  • C 4.2%
Morty Proxy This is a proxified and sanitized view of the page, visit original site.