e3nn-jax 0.19.0

Equivariant convolutional neural networks for the group E(3) of 3 dimensional rotations, translations, and mirrors.

e3nn-jax

:rocket: 44% faster than pytorch*

*Speed comparison done with a full model (MACE) during training (revMD-17) on a GPU (NVIDIA RTX A5000)

Documentation

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}
}