zuko
awesome-normalizing-flows
zuko | awesome-normalizing-flows | |
---|---|---|
1 | 1 | |
253 | 1,313 | |
5.1% | - | |
7.8 | 3.6 | |
about 1 month ago | about 1 month ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
zuko
-
[P] Zuko, a fresh approach to normalizing flows in PyTorch
Zuko already has a few users, including my research lab, but I would love to see it grow further and make it a true community project. If you are interested in normalizing flows, you can take a look at the repository francois-rozet/zuko or the documentation. Cheers!
awesome-normalizing-flows
-
[D] Understanding Generative Flow
I would recommend this list of resources on github to get you started. In particular, I highly recommend this lecture by Marcus Brubaker et al which explains the essential components that you need: linear transformations, coupling layers and the multiscale architecture.
What are some alternatives?
nflows - Normalizing flows in PyTorch
PyMC - Bayesian Modeling and Probabilistic Programming in Python
flowtorch - This library would form a permanent home for reusable components for deep probabilistic programming. The library would form and harness a community of users and contributors by focusing initially on complete infra and documentation for how to use and create components.
FrEIA - Framework for Easily Invertible Architectures
autoregressive - :kiwi_fruit: Autoregressive Models in PyTorch.
InvertibleNetworks.jl - A Julia framework for invertible neural networks
vbmc - Variational Bayesian Monte Carlo (VBMC) algorithm for posterior and model inference in MATLAB
Tensorflow-iOS
pyro - Deep universal probabilistic programming with Python and PyTorch