Skip to main content

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

Project description

e3nn

Coverage Status

E(3) is the Euclidean group in dimension 3. That is the group of rotations, translations and mirror. e3nn is a pytorch library that aims to create E(3) equivariant neural networks.

Installation

After having installed pytorch_geometric run the command:

pip install e3nn

To get the CUDA kernels read the instructions in INSTALL.md.

Example

from functools import partial

import torch

from e3nn import Kernel, rs
from e3nn.non_linearities.norm import Norm
from e3nn.non_linearities.rescaled_act import swish
from e3nn.point.operations import Convolution
from e3nn.radial import GaussianRadialModel

# Define the input and output representations
Rs_in = [(1, 0), (2, 1)]  # Input = One scalar plus two vectors
Rs_out = [(1, 1)]  # Output = One single vector

# Radial model:  R+ -> R^d
RadialModel = partial(GaussianRadialModel, max_radius=3.0, number_of_basis=3, h=100, L=1, act=swish)

# kernel: composed on a radial part that contains the learned parameters
#  and an angular part given by the spherical hamonics and the Clebsch-Gordan coefficients
K = partial(Kernel, RadialModel=RadialModel)

# Create the convolution module
conv = Convolution(K(Rs_in, Rs_out))

# Module to compute the norm of each irreducible component
norm = Norm(Rs_out)


n = 5  # number of input points
features = rs.randn(1, n, Rs_in, requires_grad=True)
in_geometry = torch.randn(1, n, 3)
out_geometry = torch.zeros(1, 1, 3)  # One point at the origin


out = norm(conv(features, in_geometry, out_geometry))
out.backward()

print(out)
print(features.grad)

Hierarchy

  • e3nn contains the library
    • e3nn/o3.py O(3) irreducible representations
    • e3nn/rsh.py real spherical harmonics
    • e3nn/rs.py geometrical tensor representations
    • e3nn/image contains voxels linear operations
    • e3nn/point contains points linear operations
    • e3nn/non_linearities non linearities operations
  • examples simple scripts and experiments

Citing

DOI

@software{e3nn_2020_3723557,
  author       = {Mario Geiger and
                  Tess Smidt and
                  Benjamin K. Miller and
                  Wouter Boomsma and
                  Kostiantyn Lapchevskyi and
                  Maurice Weiler and
                  Michał Tyszkiewicz and
                  Jes Frellsen},
  title        = {github.com/e3nn/e3nn},
  month        = may,
  year         = 2020,
  publisher    = {Zenodo},
  version      = {0.0.0},
  doi          = {10.5281/zenodo.3723557},
  url          = {https://doi.org/10.5281/zenodo.3723557}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

e3nn-0.0.2.tar.gz (313.5 kB view details)

Uploaded Source

Built Distribution

e3nn-0.0.2-py3-none-any.whl (406.5 kB view details)

Uploaded Python 3

File details

Details for the file e3nn-0.0.2.tar.gz.

File metadata

  • Download URL: e3nn-0.0.2.tar.gz
  • Upload date:
  • Size: 313.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/47.1.0 requests-toolbelt/0.9.1 tqdm/4.49.0 CPython/3.8.5

File hashes

Hashes for e3nn-0.0.2.tar.gz
Algorithm Hash digest
SHA256 05419a3f19c8846cc319a518befa390e6f5cea1615281ce584313a8eb157543d
MD5 2aebac22292d1ae1678a3f3f36a70733
BLAKE2b-256 eae6070769840bdfbcc11584d7c49ce34e6dc05b22244da3e9aa74e274530fd0

See more details on using hashes here.

File details

Details for the file e3nn-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: e3nn-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 406.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/47.1.0 requests-toolbelt/0.9.1 tqdm/4.49.0 CPython/3.8.5

File hashes

Hashes for e3nn-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 70d03ee5dd9873c57beb93c399a1ddef25c063bddde6387aea821ef9cbf42565
MD5 db7ddd13f2e342d876fdf8ff1583cc3b
BLAKE2b-256 e42d20aba2f7af829f9b529378061ba77c56a35761e560f0f8dc4ae4f482cdf3

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page