PyTorch geometric


Topic | v1 | created by janarez |
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.


Relations

used by Graph convolutional networks (GCN)

Generalization of neural networks to arbitrary graphs.

relates to Spektral

Spektral is a Python library for graph deep learning, based on the Keras API and TensorFlow 2. The ma...


Edit details Edit relations Attach new author Attach new topic Attach new resource
Resources

treated in PyTorch geometric colab notebooks

10.0 rating 1.0 level 10.0 clarity 5.0 background – 1 rating

Simple colab notebooks that practically introduce you to the world of Graph Neural Networks with PyTo...

has official PyTorch geometric documentation

8.0 rating 3.0 level 8.0 clarity 3.0 background – 1 rating

PyTorch Geometric is a geometric deep learning extension library for PyTorch.