e3nn: a modular PyTorch framework for Euclidean neural networks
Welcome!e3nn
!This is the website for the e3nn
repository
e3nn-jax Doc
e3nn-torch Doc
E(3) is the Euclidean group in dimension 3. That is the group of rotations, translations and mirror.
e3nn-torch
and e3nn-jax
are respectively pytorch and jax libraries that aims to create E(3) equivariant neural networks.
If you’d like to generally learn what e3nn
is and what it’s used for, check out some of previously recorded talks and skimming some of the papers. If you’d like to try out e3nn
, the first step is to install it.
Once you have e3nn
up and running, try out the Jupyter notebooks in e3nn_tutorial. This will give you a feel for the primary data types and classes in e3nn
. You can also dive into more rigorous math resources. This reading will be helpful for parsing even the most techincal parts of the relevant papers.
If you want to talk to other folks using e3nn
, you are most welcome to join our Slack.
pip install --upgrade e3nn
.pip install --upgrade e3nn-jax
.The documentations are:
e3nn
makes use of group theory and representation theory. You don’t need to be knowledgeable on these topics to start using e3nn
but it might be useful to have some relevant resources handy. Some of our favorite resources are:
Some previous recorded talks on e3nn
.
2020/11 Euclidean Neural Networks for Physics ∩ ML, November 18, 2020. (slides // video)
2020/09 Unintended Features of E(3)NNs, Workshop on Equivariance and Data Augmentation (video // slides), University of Pennsylvania, September 4, 2020
2020/09 Lecture on Symmetry and Equivariance in ML, Berkeley Lab Deep Learning School (video // slides), Berkeley Lab, September 3, 2020.
2020/07 Neural Networks with Euclidean Symmetry for Physical Sciences, 1st Workshop on Scientific-Driven Deep Learning (SciDL) (video // slides), July 1, 2020
2020/01 An autoencoder for discrete geometry, Applied Machine Learning Days – AI and the Molecular World (video), EPFL, January 27-28, 2020, Lausanne, Switzerland
2019/12 Euclidean Neural Networks for Emulating Ab Initio Calculations and Generating Atomic Geometries, eScience Institute Seminar (video), University of Washington, Seattle, WA
2019/09 Euclidean Neural Networks for Emulating Ab Initio Calculations and Generating Atomic Geometries, Workshop I: From Passive to Active: Generative and Reinforcement Learning with Physics, (video // slides), IPAM at UCLA, Los Angeles, CA
A poster overview of the e3nn
framework.
Please see this repo for an up to date list of papers on equivariant networks.
The e3nn
developers and several collaborators discuss ideas and help each other out with projects via Slack. If you’d like to join the Slack, please send an email to Mario geiger.mario@gmail.com
.
To get help with a question or code bug, please go on e3nn-jax:discussions or e3nn-torch:discussions.
To get involved with the development and improvement of e3nn
, please send an email to geiger.mario@gmail.com
.
e3nn
Team(aka the people answering pull-requests)
e3nn
’s BDFL, geiger.mario@gmail.com
)tess@e3nn.org
)
|
|