Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature: A new contrastive loss (Barlow Twins) #1259

Merged
merged 23 commits into from Jul 23, 2021

Conversation

Nimrais
Copy link
Contributor

@Nimrais Nimrais commented Jul 19, 2021

Before submitting (checklist)

  • Was this discussed/approved via a Github issue? (no need for typos and docs improvements)
  • Did you read the contribution guide?
  • Did you check the code style? catalyst-make-codestyle && catalyst-check-codestyle (pip install -U catalyst-codestyle).
  • Did you make sure to update the docs? We use Google format for all the methods and classes.
  • Did you check the docs with make check-docs?
  • Did you write any new necessary tests?
  • Did you check that your code passes the unit tests pytest . ?
  • Did you add your new functionality to the docs?
  • Did you update the CHANGELOG?
  • Did you run colab minimal CI/CD with latest and minimal requirements?

Description

Implementation of a negative-free contrastive loss from Barlow Twins: Self-Supervised Learning via Redundancy Reduction.

Related Issue

Type of Change

  • Examples / docs / tutorials / contributors update
  • Bug fix (non-breaking change which fixes an issue)
  • Improvement (non-breaking change which improves an existing feature)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)

PR review

Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.

FAQ

Please review the FAQ before submitting an issue:

@Nimrais
Copy link
Contributor Author

Nimrais commented Jul 19, 2021

I have run pytest . but test_reid_pipeline fails. I am sure it's not dependent on my code but it can be connected with my machine (apple M1). The test fails on assert runner.loader_metrics["cmc01"] > 0.7.

@Nimrais Nimrais changed the title Feature: Barlow Twins loss as a new contrastive loss Feature: Barlow Twins loss a new contrastive loss Jul 20, 2021
@Nimrais Nimrais changed the title Feature: Barlow Twins loss a new contrastive loss Feature: A new contrastive loss (Barlow Twins) Jul 20, 2021
@Scitator
Copy link
Member

I have run pytest . but test_reid_pipeline fails. I am sure it's not dependent on my code but it can be connected with my machine (apple M1). The test fails on assert runner.loader_metrics["cmc01"] > 0.7.

that's why we have stable GitHub actions tests :)

@pep8speaks
Copy link

pep8speaks commented Jul 22, 2021

Hello @Nimrais! Thanks for updating this PR. We checked the lines you've touched for PEP 8 issues, and found:

There are currently no PEP 8 issues detected in this Pull Request. Cheers! 🍻

Comment last updated at 2021-07-23 11:39:46 UTC

@mergify
Copy link

mergify bot commented Jul 22, 2021

This pull request is now in conflicts. @Nimrais, could you fix it? 🙏

@Scitator Scitator merged commit ce79bbe into catalyst-team:master Jul 23, 2021
@Nimrais Nimrais deleted the barlow-twins branch July 23, 2021 18:48
@Nimrais Nimrais restored the barlow-twins branch July 23, 2021 18:48
@Nimrais Nimrais deleted the barlow-twins branch July 23, 2021 18:48
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants