Equivariant convolutional neural networks for the group E(3) of 3 dimensional rotations, translations, and mirrors.
Project description
e3nn-jax ![Coverage Status](https://pypi-camo.freetls.fastly.net/dc3cc024a24a789aa6b4a50e42f3f4afe5bf800c/68747470733a2f2f636f766572616c6c732e696f2f7265706f732f6769746875622f65336e6e2f65336e6e2d6a61782f62616467652e7376673f6272616e63683d6d61696e)
:rocket: 44% faster than pytorch*
*Speed comparison done with a full model (MACE) during training (revMD-17) on a GPU (NVIDIA RTX A5000)
Documentation ![Documentation Status](https://pypi-camo.freetls.fastly.net/63ec0459de116b7c4c1867b62ff7f0d4fd03f4cc/68747470733a2f2f72656164746865646f63732e6f72672f70726f6a656374732f65336e6e2d6a61782f62616467652f3f76657273696f6e3d6c6174657374)
Please always check the ChangeLog for breaking changes.
Installation
To install the latest released version:
pip install --upgrade e3nn-jax
To install the latest GitHub version:
pip install git+https://github.com/e3nn/e3nn-jax.git
Need Help?
Ask a question in the discussions tab.
What is different from the PyTorch version?
The main difference is the presence of the class IrrepsArray
.
IrrepsArray
contains the irreps (Irreps
) along with the data array.
Citing
@misc{e3nn_paper,
doi = {10.48550/ARXIV.2207.09453},
url = {https://arxiv.org/abs/2207.09453},
author = {Geiger, Mario and Smidt, Tess},
keywords = {Machine Learning (cs.LG), Artificial Intelligence (cs.AI), Neural and Evolutionary Computing (cs.NE), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {e3nn: Euclidean Neural Networks},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
Project details
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
e3nn_jax-0.19.1.tar.gz
(121.3 kB
view hashes)
Built Distribution
e3nn_jax-0.19.1-py3-none-any.whl
(151.2 kB
view hashes)
Close
Hashes for e3nn_jax-0.19.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 676ad6e7c1fe67c365342e3455c62593415818732922b1adf7173d4842bfb0da |
|
MD5 | 290bb7c6d7d32c69b4831ec4b032caa1 |
|
BLAKE2b-256 | e9182d41104e365526865233af6b6f69416d3f94725b0f64651785645e46ec69 |