e3nn/e3nn-jax

jax library for E3 Equivariant Neural Networks

52
/ 100
Established

This library is for researchers and machine learning engineers working with 3D data, particularly in fields like molecular modeling or materials science. It provides tools to build neural networks that inherently understand symmetries and rotations in 3D space. You input 3D data representations (like atomic positions and features) and get out predictions or embeddings that respect the geometry of the system.

224 stars. Used by 2 other packages. No commits in the last 6 months. Available on PyPI.

Use this if you are developing machine learning models for 3D data where rotational and reflectional symmetries are important, and you need a high-performance JAX-based solution.

Not ideal if your data is not inherently 3D or if the symmetries of 3D space are not a critical aspect of your modeling problem.

molecular-modeling materials-science computational-chemistry 3d-data-analysis physics-based-ai
Stale 6m
Maintenance 2 / 25
Adoption 12 / 25
Maturity 25 / 25
Community 13 / 25

How are scores calculated?

Stars

224

Forks

20

Language

Python

License

Apache-2.0

Last pushed

Aug 25, 2025

Commits (30d)

0

Dependencies

5

Reverse dependents

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/e3nn/e3nn-jax"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.