luuuyi/S3FD.PyTorch

A higher performance PyTorch implementation of S3FD

S3FD in PyTorch

A PyTorch implementation of S3FD: Single Shot Scale-invariant Face Detector. The official code in Caffe can be found here.

WIDER Face Performance

Subset	Original Caffe	PyTorch Implementation
Easy	93.7%	94.1%
Medium	92.4%	92.9%
Hard	85.2%	85.4%

Component

• [√] Max-out background label
• [√] Scale compensation anchor matching strategy
• [√] Scale-equitable framework

Contents

• Installation
• Training
• Evaluation
• References

Installation

1. Install PyTorch-0.4.0 according to your environment.

2. Clone this repository. We will call the cloned directory as $S3FD_ROOT.

git clone https://github.com/luuuyi/S3FD.PyTorch.git

3. Compile the nms:

./make.sh

Note: We currently only support PyTorch-0.4.0 and Python 3+.

Training

1. Download WIDER FACE dataset, place the images under this directory:

$S3FD_ROOT/data/WIDER_FACE/images

2. Convert WIDER FACE annotations to VOC format or download our converted annotations, place them under this directory:

$S3FD_ROOT/data/WIDER_FACE/annotations

3. Download VGG Pretrained Model from here, place it under this directory:

$S3FD_ROOT/weights

4. Train the model using WIDER FACE(You should modify below file depend on your setting):

cd $S3FD_ROOT/
./train_s3fd.sh

Evaluation(WIDER Face)

1. Evaluate the trained model using:(You should modify below file depend on your setting)

./test_s3fd.sh

2. If you can use Matlab, downloading official eval tools to evaluate the performance. If you use Python, clone this repo WiderFace-Evaluation to evaluate the performance.

References

• Official release (Caffe)

• A huge thank you to FaceBoxes ports in PyTorch that have been helpful:

  • FaceBoxes.PyTorch

  Note: If you can not download the converted annotations, the provided images and the trained model through the above links, you can download them through BaiduYun.