Coverage Status DOI

Documentation | Code | ChangeLog | Colab

The aim of this library it to help the developement of E3 equivariant neural networks. It contains fundamental mathematical operations such as tensor products and spherical harmonics.



Previous version

e3nn has been recently refactored. The last version before refactoring can be installed with the command pip install e3nn==0.1.1


We are happy to help! The best way to get help on e3nn is to submit a Question or Bug Report.

Want to get involved? Great!

If you want to get involved in and contribute to the development, improvement, and application of e3nn, introduce yourself with Project Wanted.

Code of conduct

Our community abides by the Contributor Covenant Code of Conduct.


  author       = {Mario Geiger and
                  Tess Smidt and
                  Benjamin K. Miller and
                  Wouter Boomsma and
                  Kostiantyn Lapchevskyi and
                  Maurice Weiler and
                  Michał Tyszkiewicz and
                  Alby M. and
                  Bradley Dice and
                  Jes Frellsen and
                  Nuri Jung and
                  Sophia Sanborn and
                  Josh Rackers and
                  Simon Batzner},
  title        = {e3nn/e3nn 0.2.3},
  month        = feb,
  year         = 2021,
  publisher    = {Zenodo},
  version      = {0.2.3},
  doi          = {10.5281/zenodo.4557591},
  url          = {https://doi.org/10.5281/zenodo.4557591}

Indices and tables