Geometric Deep Learning Python Packages

torch-geometric

Graph Neural Network Library for PyTorch

openequivariance

OpenEquivariance: a fast, open-source GPU JIT kernel generator for the Clebsch-Gordon Tensor Product.

pyg-nightly

Graph Neural Network Library for PyTorch

dgllife

Python package for graph neural networks in chemistry and biology

torch-cluster

PyTorch Extension Library of Optimized Graph Cluster Algorithms

pypose

A library for differentiable robotics on manifolds.

avitai-artifex

Generative modeling for JAX/Flax NNX: VAEs, GANs, DDPM/DDIM/score/DiT/latent diffusion, normalizing flows, energy-based, autoregressive and geometric (SE(3), protein, point cloud, mesh) models; image, text, audio, molecular, protein, tabular and time-series modalities; a shared Trainer with callbacks and extensions; evaluation through calibrax.

sphericart-torch

Multi-language library for the calculation of spherical harmonics in Cartesian coordinates

sphericart

Multi-language library for the calculation of spherical harmonics in Cartesian coordinates

torch-spline-conv

Implementation of the Spline-Based Convolution Operator of SplineCNN in PyTorch

graphein

Protein Graph Library

sphericart-jax

Multi-language library for the calculation of spherical harmonics in Cartesian coordinates

keras-hexagdly

Keras 3 hexagonal CNN layers (HexagDLy port) for hexagonally-sampled data — IACT/Cherenkov cameras, etc. — Support for hls4ml in progress

neuralogic

PyNeuraLogic lets you use Python to create Differentiable Logic Programs

escnn

Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/

cellshape

3D shape analysis using deep learning

stellargraph

StellarGraph - Machine Learning on Graphs

atom-jepa

Atom-JEPA: Joint-Embedding Predictive Architecture for 3D Atomistic Systems

pytorch-hexagdly

Process hexagonally sampled data with PyTorch

deltaconv

Code for the SIGGRAPH 2022 paper "DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds."

openequivariance-extjax

OpenEquivariance: a fast, open-source GPU JIT kernel generator for the Clebsch-Gordon Tensor Product.

vn-transformer

A Transformer made of Rotation-equivariant Attention using Vector Neurons

graphgallery

GraphGallery is a gallery for benchmarking Graph Neural Networks

aidsorb

Python package for deep learning on porous materials and beyond.