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 examples see test_on_images.ipynb
.
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-0.0.3.tar.gz
(6.9 kB
view hashes)
Built Distribution
Close
Hashes for torch_mtcnn-0.0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b90002cd9b566b9581d0922bf04f90c2a4382b7dc31492806ac5c375faa9d9d2 |
|
MD5 | f8c04bc0661e913376b73688cc3fa44c |
|
BLAKE2b-256 | fbf948d4d86400130752679832f854b479bf282086d26a0d16b80e494fa461cd |