atong01 / conditional-flow-matching

TorchCFM: a Conditional Flow Matching library
https://arxiv.org/abs/2302.00482
MIT License
1.25k stars 101 forks source link

1.0.6 release #87

Closed kilianFatras closed 11 months ago

kilianFatras commented 11 months ago

What does this PR do?

  1. This PR fixes SDE class bugs in utils and mnist notebooks. There was a - sign instead of a + sign in the notebooks and the diffusion coefficient was not correct.
  2. This PR refactors the example folder to split the examples into different folders.
  3. This PR adds two new tutorials: one on Flow Matching and another one on minibatch OT

Fixes #85

Before submitting

Did you have fun?

Make sure you had fun coding 🙃

review-notebook-app[bot] commented 11 months ago

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

codecov[bot] commented 11 months ago

Codecov Report

All modified and coverable lines are covered by tests :white_check_mark:

Comparison is base (b29d418) 35.90% compared to head (fafa308) 35.92%.

Additional details and impacted files ```diff @@ Coverage Diff @@ ## main #87 +/- ## ========================================== + Coverage 35.90% 35.92% +0.01% ========================================== Files 67 67 Lines 7419 7399 -20 ========================================== - Hits 2664 2658 -6 + Misses 4755 4741 -14 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.