PyTorch geometric

Topic history | v1 (current) | created by janarez

Details

PyTorch geometric

| created by janarez | Add topic "PyTorch geometric"
Title
PyTorch geometric
Description
PyTorch Geometric (PyG) is a geometric deep learning extension library for PyTorch. It consists of various methods for deep learning on graphs and other irregular structures, also known as geometric deep learning, from a variety of published papers. In addition, it consists of an easy-to-use mini-batch loader for many small and single giant graphs, multi gpu-support, a large number of common benchmark datasets (based on simple interfaces to create your own), and helpful transforms, both for learning on arbitrary graphs as well as on 3D meshes or point clouds.
Link
https://github.com/rusty1s/pytorch_geometric

resources

has official PyTorch geometric documentation
v1 | attached by janarez | Add topic "PyTorch geometric"
treated in PyTorch geometric colab notebooks
v1 | attached by janarez | Add topic "PyTorch geometric"

authors

This topic has no history of related authors.

topics

(detached) Graph convolutional networks (GCN)
| detached by jjones | Add topic "Graph neural network"
used by
v1 | attached by janarez | Add topic "PyTorch geometric"
relates to Spektral
v1 | attached by janarez | Add topic "PyTorch geometric"
uses Graph neural network
v1 | attached by jjones | Add topic "Graph neural network"