Py-torch-geometric

Jul 20, 2023

Graph neural network library for PyTorch

PyG PyTorch Geometric is a library built upon PyTorch to easily write and train Graph Neural Networks GNNs for a wide range of applications related to structured data.

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 easy-to-use mini-batch loaders for operating on many small and single giant graphs, multi GPU-support, torch.compile support, DataPipe support, a large number of common benchmark datasets based on simple interfaces to create your own, the GraphGym experiment manager, and helpful transforms, both for learning on arbitrary graphs as well as on 3D meshes or point clouds.



Checkout these related ports:
  • Zoneinfo - Updated timezone definitions
  • Zine - Simple and opinionated tool to build your own magazine
  • Ytree - DOS-XTREE(tm) look-a-like file manager
  • Yaunc - Yet another uptimes.net client
  • Xtypo - X-based keyboard trainer
  • Xtar - View and manipulate contents of a tar file
  • Xtail - Watches the growth of files or directories
  • Xplr - Hackable, minimal, fast TUI file explorer
  • Xosd - X11 on-screen-display program and library
  • Xless - X11-based viewer for text files
  • Xiphos - Bible interface utilizing the sword framework
  • Xgboost - Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT, GBM)
  • Xgas - The animated simulation of an ideal gas
  • Xfce4-wm-themes - Additional themes for xfwm4
  • Xfce4-weather-plugin - Weather plugin for the Xfce panel