Metadata-Version: 2.1
Name: torch-mtcnn
Version: 0.0.3
Summary: Implementation of MTCNN using Pytorch.
Home-page: https://github.com/khrlimam/mtcnn-pytorch
Author: Dan Antoshchenko
License: UNKNOWN
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](https://arxiv.org/abs/1604.02878).
        
        ## Example
        ![example of a face detection](https://github.com/TropComplique/mtcnn-pytorch/blob/master/images/example.png)
        
        ## How to use it
        Install the package with pip: `pip install torch-mtcnn`
        ```python
        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:
        * [pangyupo/mxnet_mtcnn_face_detection](https://github.com/pangyupo/mxnet_mtcnn_face_detection)  
        
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
