Basic flowjax implementation in jax.
Project description
flowjax
Normalising flow implementations in jax.
So far supports:
-
Affine coupling flows/RealNVP for conditional/unconditional density estimation (Dinh et al.)
-
Neural spline coupling flows for conditional/unconditional density estimation (Durkan et al.)
-
Block neural autoregressive flows for unconditional density estimation (De Cao et al.)
See examples.
Authors
flowjax was written by Daniel Ward <danielward27@outlook.com>.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
flowjax-0.3.0.tar.gz
(11.0 kB
view hashes)
Built Distribution
flowjax-0.3.0-py3-none-any.whl
(13.8 kB
view hashes)
