pytorch implementation of inference stage of face detection algorithm described in
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks.

Just download the repository and then do this

from src import detect_faces
from PIL import Image

image = Image.open('image.jpg')
bounding_boxes, landmarks = detect_faces(image)

For examples see test_on_images.ipynb.

• pytorch 0.2
• Pillow, numpy

This implementation is heavily inspired by:

• pangyupo/mxnet_mtcnn_face_detection