• Stars
    star
    126
  • Rank 279,077 (Top 6 %)
  • Language
    Jupyter Notebook
  • Created about 5 years ago
  • Updated about 5 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Pytorch Implementation of the paper MixMatch: A Holistic Approach to Semi-Supervised Learning (https://arxiv.org/pdf/1905.02249.pdf)

[WIP] MixMatch: A Holistic Approach to Semi-Supervised Learning

A Pytorch Implementation of the paper MixMatch: A Holistic Approach to Semi-Supervised Learning [paper]. Till it is no longer a WIP check notebook for latest code.

TO-DO

  • Train on CIFAR10 data.
  • Add training code for CIFAR10 with WideResnet28 from here.

Dependencies

pip install <pytorch-latest.whl url>

To use this layer:

from layer import mixmatch, MixMatchLoss