pytorch-geometric.readthedocs.io Open in urlscan Pro
2606:4700::6811:2052  Public Scan

Form analysis
2 forms found in the DOM

GET search.html

<form id="rtd-search-form" class="wy-form" action="search.html" method="get">
  <input type="text" name="q" placeholder="Search docs">
  <input type="hidden" name="check_keywords" value="yes">
  <input type="hidden" name="area" value="default">
</form>

GET //readthedocs.org/projects/pytorch-geometric/search/

<form id="flyout-search-form" class="wy-form" target="_blank" action="//readthedocs.org/projects/pytorch-geometric/search/" method="get">
  <input type="text" name="q" aria-label="Search docs" placeholder="Search docs">
</form>

Text Content

latest


Notes

 * Installation
   * Quick Start
   * Installation via Anaconda
   * Installation via Pip Wheels
   * Installation from Source
   * Frequently Asked Questions
 * Introduction by Example
   * Data Handling of Graphs
   * Common Benchmark Datasets
   * Mini-batches
   * Data Transforms
   * Learning Methods on Graphs
   * Exercises
 * Creating Message Passing Networks
   * The “MessagePassing” Base Class
   * Implementing the GCN Layer
   * Implementing the Edge Convolution
   * Exercises
 * Creating Your Own Datasets
   * Creating “In Memory Datasets”
   * Creating “Larger” Datasets
   * Frequently Asked Questions
   * Exercises
 * Heterogeneous Graph Learning
   * Example Graph
   * Creating Heterogeneous Graphs
   * Heterogeneous Graph Transformations
   * Creating Heterogeneous GNNs
   * Heterogeneous Graph Samplers
 * Loading Graphs from CSV
 * Managing Experiments with GraphGym
   * Highlights
   * Why GraphGym?
   * Basic Usage
   * In-Depth Usage
   * Customizing GraphGym
 * Advanced Mini-Batching
   * Pairs of Graphs
   * Bipartite Graphs
   * Batching Along New Dimensions
 * Memory-Efficient Aggregations
 * TorchScript Support
   * Converting GNN Models
   * Creating Jittable GNN Operators
 * GNN Cheatsheet
   * Graph Neural Network Operators
   * Heterogeneous Graph Neural Network Operators
   * Hypergraph Neural Network Operators
   * Point Cloud Neural Network Operators
 * Dataset Cheatsheet
 * Colab Notebooks and Video Tutorials
 * External Resources

Package Reference

 * torch_geometric
 * torch_geometric.nn
   * Convolutional Layers
   * Dense Convolutional Layers
   * Normalization Layers
   * Global Pooling Layers
   * Pooling Layers
   * Dense Pooling Layers
   * Unpooling Layers
   * Models
   * Functional
   * Model Transformations
   * DataParallel Layers
 * torch_geometric.data
 * torch_geometric.loader
 * torch_geometric.datasets
 * torch_geometric.transforms
 * torch_geometric.utils
 * torch_geometric.graphgym
   * Workflow and Register Modules
   * Model Modules
   * Utility Modules
 * torch_geometric.profile

pytorch_geometric
 * »
 * PyG Documentation
 * Edit on GitHub

--------------------------------------------------------------------------------


PYG DOCUMENTATION¶

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, DataPipe support,
distributed graph learning via Quiver, 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. Click here to join our Slack
community!

Notes

 * Installation
 * Introduction by Example
 * Creating Message Passing Networks
 * Creating Your Own Datasets
 * Heterogeneous Graph Learning
 * Loading Graphs from CSV
 * Managing Experiments with GraphGym
 * Advanced Mini-Batching
 * Memory-Efficient Aggregations
 * TorchScript Support
 * GNN Cheatsheet
 * Dataset Cheatsheet
 * Colab Notebooks and Video Tutorials
 * External Resources

Package Reference

 * torch_geometric
 * torch_geometric.nn
 * torch_geometric.data
 * torch_geometric.loader
 * torch_geometric.datasets
 * torch_geometric.transforms
 * torch_geometric.utils
 * torch_geometric.graphgym
 * torch_geometric.profile


INDICES AND TABLES¶

 * Index

 * Module Index

Next

--------------------------------------------------------------------------------

Love Documentation? Write the Docs is for people like you! Join our virtual
conferences or Slack.
Community Ad

© Copyright 2022, Matthias Fey. Revision b0cec1df.

Built with Sphinx using a theme provided by Read the Docs.
Read the Docs v: latest
Versions latest 2.0.3 2.0.2 2.0.1 2.0.0 1.7.2 1.7.1 1.7.0 1.6.3 1.6.1 1.6.0
1.5.0 1.4.3 1.4.2 1.4.1 1.3.2 1.3.1 1.3.0 On Read the Docs Project Home Builds
Downloads On GitHub View Edit Search


--------------------------------------------------------------------------------

Hosted by Read the Docs · Privacy Policy