VISSL is a computer VIsion library for state-of-the-art Self-Supervised Learning research with PyTorch. VISSL aims to accelerate research cycle in self-supervised learning: from designing a new self-supervised task to evaluating the learned representations.

Within Facebook AI, VISSL has been used to power research projects such as SwAV.

Please find installation instructions in INSTALL.md.

After installation, please see GETTING_STARTED.md for how to run various ssl tasks.

VISSL is released under CC-NC 4.0 International license.

Get started with VISSL by trying one of the [tutorial notebooks][tutorials/].

Learn more about the API by reading the VISSL [documentation](TODO: prigoyal).

We provide a large set of baseline results and trained models available for download in the VISSL Model Zoo.

We welcome new contributions to VISSL and we will be actively maintaining this library! Please refer to CONTRIBUTING.md for full instructions on how to run the code, tests and linter, and submit your pull requests.

VISSL is written and maintained by the Facebook AI Research Computer Vision Team.

If you find VISSL useful in your research, please cite:

@misc{goyal2020vissl,
  author =       {Priya Goyal and ... and Armand Joulin},
  title =        {VISSL},
  howpublished = {\url{https://github.com/facebookresearch/vissl}},
  year =         {2020}
}