FaceBoxes in PyTorch
By Zisian Wong, Shifeng Zhang
A PyTorch implementation of FaceBoxes: A CPU Real-time Face Detector with High Accuracy. The official code in Caffe can be found here.
Performance
| Dataset | Original Caffe | PyTorch Implementation | |:-|:-:|:-:| | AFW | 98.98 % | 98.47% | | PASCAL | 96.77 % | 96.84% | | FDDB | 95.90 % | 95.44% |
Citation
Please cite the paper in your publications if it helps your research:
@inproceedings{zhang2017faceboxes,
title = {Faceboxes: A CPU Real-time Face Detector with High Accuracy},
author = {Zhang, Shifeng and Zhu, Xiangyu and Lei, Zhen and Shi, Hailin and Wang, Xiaobo and Li, Stan Z.},
booktitle = {IJCB},
year = {2017}
}
Contents
Installation
Install PyTorch >= v1.0.0 following official instruction.
Clone this repository. We will call the cloned directory as $FaceBoxes_ROOT
.
git clone https://github.com/zisianw/FaceBoxes.PyTorch.git
Compile the nms:
./make.sh
_Note: Codes are based on Python 3+._
Training
Download WIDER FACE dataset, place the images under this directory: Shell $FaceBoxes_ROOT/data/WIDER_FACE/images
Convert WIDER FACE annotations to VOC format or download our converted annotations, place them under this directory:
$FaceBoxes_ROOT/data/WIDER_FACE/annotations
Train the model using WIDER FACE:
cd $FaceBoxes_ROOT/
python3 train.py
If you do not wish to train the model, you can download our pre-trained model and save it in $FaceBoxes_ROOT/weights
.
Evaluation
Download the images of AFW, PASCAL Face and FDDB to:
$FaceBoxes_ROOT/data/AFW/images/$FaceBoxes_ROOT/data/PASCAL/images/$FaceBoxes_ROOT/data/FDDB/images/
Evaluate the trained model using:
# dataset choices = ['AFW', 'PASCAL', 'FDDB']python3 test.py --dataset FDDB# evaluate using cpupython3 test.py --cpu
Download eval_tool to evaluate the performance.
References
Official release (Caffe)
A huge thank you to SSD ports in PyTorch that have been helpful:
_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._