symm-learning 0.2.21

Torch modules and utilities of equivariant/invariant learning

Symmetric Learning

Lightweight python package for doing geometric deep learning using ESCNN. This package simply holds:

• Generic equivariant torch models and modules that are not present in ESCNN.
• Linear algebra utilities when working with symmetric vector spaces.
• Statistics utilities for symmetric random variables.

Installation

pip install symm-learning
# or
git clone https://github.com/Danfoa/symmetric_learning
cd symmetric_learning
pip install -e .

Documentation

Updated documentation can be found here. The repository is structured as follows:

• Linear Algebra Utility functions for doing linear algebra on symmetric vector spaces, including: least squares solutions, group invariant projections, disentangled/isotypic decompositions, and more.
• Statistics Functions for computing statistics (e.g., mean, variance, covariance) of symmetric random variables.
• Models A collection of equivariant neural network architectures.
• Neural Network Equivariant Modules A collection of neural network modules that are equivariant to group actions, specifically targeted at processing vector-valued data and time series data:
  • Activations
  • Pooling
  • Normalization
  • Distributions
  • Convolution
  • Disentangled