TempMatch (Temperatue Match) is a package for exploring and using the Semi-Supervised learning algorithm developed by Clarifai
- Benchmark Results: https://github.com/levinwil/TempMatch/tree/main/benchmarks
- Issues: https://github.com/levinwil/TempMatch/issues
Some system/package requirements:
- Python: 3.6+
- OS: All major platforms (Linux, MacOS, Windows)
- Dependencies: numpy, torch, pillow, tqdm
The TempMatch algorithm is heavily inspired by FixMatch:
@article{sohn2020fixmatch,
title={FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence},
author={Kihyuk Sohn and David Berthelot and Chun-Liang Li and Zizhao Zhang and Nicholas Carlini and Ekin D. Cubuk and Alex Kurakin and Han Zhang and Colin Raffel},
journal={arXiv preprint arXiv:2001.07685},
year={2020},
}