MMFashion is an open source visual fashion analysis toolbox based on PyTorch. It is a part of the open-mmlab project developed by Multimedia Lab, CUHK.

[2019-11-01] MMFashion v0.1 is released.

• Flexible: modular design and easy to extend

• Friendly: off-the-shelf models for layman users

• Comprehensive: support a wide spectrum of fashion analysis tasks

  • Fashion Attribute Prediction
  • Fashion Recognition and Retrieval
  • Fashion Landmark Detection
  • Fashion Parsing and Segmentation
  • Fashion Compatibility and Recommendation

• Python 3.5+
• PyTorch 1.0.0+
• mmcv

1. Install from pypi.

   pip install mmfashion

2. Install from source.

   git clone https://github.com/open-mmlab/mmfashion.git
   python setup.py install

Please refer to GETTING_STARTED.md for the basic usage of MMFashion.

Please refer to DATA_PREPARATION.md for the dataset specifics of MMFashion.

Please refer to MODEL_ZOO.md for a comprehensive set of pre-trained models in MMFashion.

We appreciate all contributions to improve MMFashion. Please refer to CONTRIBUTING.md for the contributing guideline.

• fashion-detection
• fashion-landmarks
• fashion-cut

This project is released under the Apache 2.0 license.

• Xin Liu (veralauee)
• Jiancheng Li (lijiancheng0614)
• Jiaqi Wang (myownskyW7)
• Ziwei Liu (liuziwei7)