equinox and e3nn-jax

Equinox is a general-purpose neural network framework for JAX that can be used to implement equivariant architectures, while e3nn-jax is a specialized library providing pre-built E(3)-equivariant building blocks—making them complements that can be used together, with e3nn-jax offering domain-specific components for Equinox users working on geometric deep learning problems.

equinox
84
Verified
e3nn-jax
62
Established
Maintenance 16/25
Adoption 25/25
Maturity 25/25
Community 18/25
Maintenance 2/25
Adoption 22/25
Maturity 25/25
Community 13/25
Stars: 2,814
Forks: 180
Downloads: 1,237,379
Commits (30d): 3
Language: Python
License: Apache-2.0
Stars: 224
Forks: 20
Downloads: 158,867
Commits (30d): 0
Language: Python
License: Apache-2.0
No risk flags
Stale 6m

About equinox

patrick-kidger/equinox

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

About e3nn-jax

e3nn/e3nn-jax

jax library for E3 Equivariant Neural Networks

Related comparisons

Scores updated daily from GitHub, PyPI, and npm data. How scores work