Implementation of MTCNN using Pytorch.
Project description
The original work of this project is always belong to the original creator (https://github.com/TropComplique/mtcnn-pytorch). I just make this available on pypi for easy installation. To install this project just type pip install torch-mtcnn
MTCNN
pytorch
implementation of inference stage of face detection algorithm described in
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks.
Example
How to use it
Install the package with pip: pip install torch-mtcnn
from torch_mtcnn import detect_faces
from PIL import Image
image = Image.open('image.jpg')
bounding_boxes, landmarks = detect_faces(image)
For a few more examples available on the original repository (link above).
Requirements
- pytorch 0.2
- Pillow, numpy
Credit
This implementation is heavily inspired by:
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
torch-mtcnn-0.0.6.tar.gz
(7.1 kB
view hashes)
Built Distribution
Close
Hashes for torch_mtcnn-0.0.6-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9a46587c727f9320f206fdda5faa022d5e2fb73e5afff0d2da0d193a8654566b |
|
MD5 | 87ef0891b215c3dac97cd8cde4d7b962 |
|
BLAKE2b-256 | 00f2fdc89adad1a3dd325b8759a8a9b8bab26a5409d3482f5443fdf164bc7696 |