Fast and reliable face detection with RetinaFace.

This repo provides the out-of-box RetinaFace detector.

• Python 3.5+ (it may work with other versions too)
• Linux, Windows or macOS
• PyTorch (>=1.0)

While not required, for optimal performance it is highly recommended to run the code using a CUDA enabled GPU.

The easiest way to install it is using pip:

pip install git+https://github.com/elliottzheng/face-detection.git@master

from skimage import io
from face_detection import RetinaFace

detector = RetinaFace()
img= io.imread('examples/obama.jpg')
faces = detector(img)
box, landmarks, score = faces[0]

In order to specify the device (GPU or CPU) on which the code will run one can explicitly pass the device id.

from face_detection import RetinaFace
# 0 means using GPU with id 0 for inference
# default -1: means using cpu for inference
detector = RetinaFace(gpu_id=0) 

All the input images must of the same size.

Detector with CUDA process batch input faster than the same amount of single input.

from skimage import io
from face_detection import RetinaFace

detector = RetinaFace()
img= io.imread('examples/obama.jpg')
all_faces = detector([img,img]) # return faces list of all images
box, landmarks, score = all_faces[0][0]

• Network and pretrained model are from biubug6/Pytorch_Retinaface

@inproceedings{deng2019retinaface,
title={RetinaFace: Single-stage Dense Face Localisation in the Wild},
author={Deng, Jiankang and Guo, Jia and Yuxiang, Zhou and Jinke Yu and Irene Kotsia and Zafeiriou, Stefanos},
booktitle={arxiv},
year={2019}