SFD implement with pytorch
Clone or download
Latest commit bccf1d9 Jan 2, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data finish Dec 22, 2018
eval_tools add hand and head Dec 18, 2018
img modify readme Dec 10, 2018
layers finish Dec 22, 2018
tmp finish Dec 22, 2018
tools fixed bug Dec 23, 2018
utils finish Dec 22, 2018
.gitignore add hand and head Dec 18, 2018
README.md update readme Jan 2, 2019
demo.py finish Dec 22, 2018
prepare_hand_dataset.py add hand and head Dec 18, 2018
prepare_wider_data.py add hand and head Dec 18, 2018
s3fd.py fixed bug Dec 23, 2018
train.py finish Dec 22, 2018

README.md

S³FD: Single Shot Scale-invariant Face Detector

A PyTorch Implementation of Single Shot Scale-invariant Face Detector

Description

Meanwhile train hand and head with S3FD,hand dataset is Egohands Dataset,head dataset is SCUT-HEAD,we can download hand model and face model

Requirement

  • pytorch 0.3
  • opencv
  • numpy
  • easydict

Prepare data

  1. download WIDER face dataset、Egohands dataset and SCUT-HEAD
  2. modify data/config.py
  3. python prepare_wider_data.py 4 python prepare_handataset.py

Train

We can choose different dataset to train different target[face,head,hand]

python train.py --batch_size 4 --dataset face\hand\head

Evalution

according to yourself dataset path,modify data/config.py

  1. Evaluate on AFW.
python afw_test.py
  1. Evaluate on FDDB
python fddb_test.py
  1. Evaluate on PASCAL face
python pascal_test.py
  1. test on WIDER FACE
python wider_test.py

Demo

you can test yourself image

python demo.py

Result

  1. AFW PASCAL FDDB
afw pascal fddb
AFW AP=99.81 paper=99.85 
PASCAL AP=98.77 paper=98.49
FDDB AP=0.975 paper=0.983
WIDER FACE:
Easy AP=0.925 paper = 0.927
Medium AP=0.925 paper = 0.924
Hard AP=0.854 paper = 0.852
  1. demo
afw

References