{"library":"e3nn-jax","type":"library","category":null,"description":"e3nn-jax is a Python library for constructing Equivariant Neural Networks (ENN) using JAX, specifically designed for the E(3) group of 3D rotations, translations, and reflections. It provides fundamental building blocks like Irreducible Representations (Irreps), spherical harmonics, and equivariant layers, enabling the design of networks that respect geometric symmetries. As of version 0.21.0, it is actively maintained with regular updates, reflecting advancements in the E(3) equivariant deep learning field.","language":"python","status":"active","version":"0.21.0","tags":["deep learning","machine learning","neural networks","equivariant networks","geometric deep learning","JAX","E(3) equivariance","3D data"],"last_verified":"Tue May 26","install":[{"cmd":"pip install e3nn-jax","imports":["from e3nn_jax import Irreps","from e3nn_jax import spherical_harmonics","from e3nn_jax import rand_irreps","from e3nn_jax.flax import Linear"]},{"cmd":"pip install --upgrade \"jax[cuda12_pip]\" -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html\npip install e3nn-jax","imports":[]}],"homepage":"https://e3nn-jax.readthedocs.io","github":"https://github.com/e3nn/e3nn-jax","docs":"https://e3nn-jax.readthedocs.io","changelog":"https://github.com/e3nn/e3nn-jax/blob/main/CHANGELOG.md","pypi":"https://pypi.org/project/e3nn-jax/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":50,"avg_install_s":25.7,"avg_import_s":5.55,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/e3nn-jax/compatibility"}}