abdulfatir/normalizing-flows

Understanding normalizing flows

43
/ 100
Emerging

This project helps machine learning researchers and practitioners understand and experiment with normalizing flows, specifically planar and radial flows. It takes in existing complex 2D data distributions and outputs transformed samples that can be used for variational inference. This is ideal for those working on probabilistic modeling and generative tasks.

132 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or student exploring generative models and want to understand how normalizing flows can transform complex probability distributions.

Not ideal if you need a production-ready, robust implementation for Variational Autoencoders (VAEs) with planar flows, as the VAE+PF implementation in this repository has known bugs.

probabilistic modeling generative models variational inference machine learning research data distribution transformation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

132

Forks

20

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 02, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/abdulfatir/normalizing-flows"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.