Skip to content

yxlijun/Faceboxes.pytorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FaceBoxes: A CPU Real-time Face Detector with High Accuracy

A PyTorch Implementation of FaceBoxes: A CPU Real-time Face Detector with High Accuracy

Description

I train faceboxes with pytorch which approachs the official code,the final model can be downloaded in faceboxes.pytorch, the ap in AFW,PASCAL_FACE and FDDB as following:

AFW PASCAL FDDB
98.32 96.35 95.2

Requirement

  • pytorch 0.3
  • opencv
  • numpy
  • easydict

Prepare data

  1. download WIDER face dataset
  2. modify data/config.py
  3. python prepare_wider_data.py

Train

python train.py --lr 0.001

Evalution

according to yourself dataset path,modify data/config.py,the evalution way is same with the official code

  1. Evaluate on AFW.
python tools/afw_test.py
  1. Evaluate on FDDB
python tools/fddb_test.py
  1. Evaluate on PASCAL face
python tools/pascal_test.py
  1. Test image
python demo.py

Result

demo demo

References

Releases

No releases published

Packages

No packages published

Languages