Skip to content
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
Branch: master
Clone or download
TropComplique Merge pull request #6 from sakhalkark/patch-3
if shape[0] is 0 then Variable throws error
Latest commit 45b3446 Mar 12, 2018

README.md

MTCNN

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

Example

example of a face detection

How to use it

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.

Requirements

  • pytorch 0.2
  • Pillow, numpy

Credit

This implementation is heavily inspired by:

You can’t perform that action at this time.