Normalizing-Flows

This repository offers an implementation of some of the most common architectures for normalizing flows. If you are here you may be interested by this nice repository https://github.com/bayesiains/nflows which contains many flow components implementation as well!

---

Installation:

pip install git+https://github.com/AWehenkel/Normalizing-Flows/

Dependencies

• torch (> 1.5)
• numpy
• umnn (pip install umnn)

---

Still in progress, you can check the models folder for basic implementation of affine and monotonic transformations and coupling or autorgressive conditioners.

---

Short tutorials:

2D toy problems

This one shows how to build simple autoregressive feed-forward normalizing flows.

Flow for images

To come...

Conditional normalizing flows

To come...

Graphical normalizing flows

To come...