---
id: e3nn
version: "0.6.0"
license: MIT
license_treatment: permissive
maintenance: aging
---

# e3nn — Equivariant convolutional neural networks for the group E(3) of 3 dimensional rotations, translations, and mirrors.

License: permissive · Maintenance: aging · Downloads: 532.7K/mo

## What it is and what it does

e3nn is a PyTorch library for building neural networks that respect Euclidean symmetries—rotations, translations, and reflections in 3D space. It provides building blocks like equivariant linear layers, tensor products, and spherical harmonics that automatically enforce these symmetries during computation, eliminating the need to manually encode geometric constraints.

The library is designed for researchers and practitioners working with 3D geometric data: point clouds, molecular structures, volumetric data, and other problems where rotational or translational invariance is a natural property of the problem. It depends on PyTorch for computation, sympy and scipy for mathematical operations, and opt_einsum_fx for tensor contraction optimization.

Use it for:

- Build neural networks for molecular property prediction that respect 3D rotational symmetry of atomic structures.
- Process point cloud data with layers that automatically handle arbitrary rotations and translations.
- Implement steerable convolutional networks for volumetric data like medical imaging or climate simulations.
- Compose custom equivariant architectures using tensor products and irreducible representations.
- Accelerate geometric deep learning research by reusing tested equivariance operations instead of deriving them from scratch.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

e3nn provides PyTorch-based operations for building E(3)-equivariant neural networks, including tensor products, spherical harmonics, and linear layers that respect rotation, translation, and mirror symmetries.

Yes, if you are building neural networks for 3D geometric or molecular data and need built-in equivariance guarantees. The library is mature enough for research use, has no known vulnerabilities, and low install friction. The aging maintenance status (182 days since last release) is a minor concern for a research tool but not a blocker if your use case aligns with the current API.

## Install

pip install e3nn
uv add e3nn
poetry add e3nn

## Installing e3nn

Before you install: Low friction installation as a pure Python wheel. Maintenance status is aging—last release was 182 days ago—but the repository remains active with recent commits and the package supports current Python versions (3.8–3.10).

License in practice: MIT license is permissive; you may use, modify, and distribute e3nn freely in commercial and private projects with minimal restrictions.

Quickstart:

pip install e3nn

import torch
from e3nn import o3

irreps_in = o3.Irreps("0e + 1o")
x = irreps_in.randn(-1)
linear = o3.Linear(irreps_in=irreps_in, irreps_out=o3.Irreps("2x0e + 2x1o"))
y = linear(x)

PyTorch must be installed before e3nn; the package requires Python ≥3.8.

Verify before relying:

- Whether opt_einsum_fx is a required runtime dependency or an optional performance enhancement.
- Stability guarantees or API compatibility policy beyond the stated breaking-change versioning scheme.

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: aging
- Downloads: 532.7K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

equivariant neural networks, E(3) equivariance pytorch, tensor product operations, spherical harmonics neural, rotation equivariant layers, 3D point cloud networks, geometric deep learning, geometric-deep-learning, equivariant-networks, pytorch-extension

[View on SkillFed](https://skillfed.io/packages/e3nn) · [View on PyPI](https://pypi.org/project/e3nn/)