https://github.com/gle-bellier/flow-matching
Annotated Flow Matching paper
https://github.com/gle-bellier/flow-matching
deep-learning flow-matching generative-ai machine-learning pytorch pytorch-lightning
Last synced: 16 days ago
JSON representation
Annotated Flow Matching paper
- Host: GitHub
- URL: https://github.com/gle-bellier/flow-matching
- Owner: gle-bellier
- Created: 2023-02-19T00:55:45.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-09-14T07:35:25.000Z (5 months ago)
- Last Synced: 2025-01-29T15:07:13.910Z (23 days ago)
- Topics: deep-learning, flow-matching, generative-ai, machine-learning, pytorch, pytorch-lightning
- Language: Jupyter Notebook
- Homepage:
- Size: 290 KB
- Stars: 160
- Watchers: 1
- Forks: 6
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Flow Matching for Generative Modeling
_notebook by Georges Le Bellier_ - [Twitter](https://twitter.com/_lebellig), [Website](https://gle-bellier.github.io)
⚠️ This is not the official implementation of the original paper.
This notebook centers around the **Flow Matching for Generative Modeling** article [1] and proposes an implementation of _Flow Matching_ in the case of _Optimal Transport conditional Vector Fields_. The implementation proposed in [2] was consulted and it inspired the use of the _Zuko_ [3] package for ODE solving and sampling. Moreover, this notebook adopts the notations of the original article and thus the numbers of the equations are the same as in the paper.
## References:
📄 [1] **Flow Matching for Generative Modeling** by Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu, Maximilian Nickel, Matt Le - [Article](https://arxiv.org/abs/2210.02747)
🐍 [2] **Flow Matching in 100 LOC** by François Rozet - [Implementation](https://gist.github.com/francois-rozet/fd6a820e052157f8ac6e2aa39e16c1aa)
🐍 [3] **Zuko** package - [Website](https://zuko.readthedocs.io/en/stable/index.html)