From the course: Learning Graph Neural Networks

Unlock this course with a free trial

Join today to access over 24,400 courses taught by industry experts.

Introducing PyTorch Geometric

Introducing PyTorch Geometric

From the course: Learning Graph Neural Networks

Start my 1-month free trial Buy for my team

Introducing PyTorch Geometric

“

- [Instructor] Before we move on to our hands-on demos, let's quickly discuss the library that we are going to be using for our graph neural networks, PyTorch Geometric. PyTorch Geometric, also called PyG, is an extension library for PyTorch, designed to facilitate the development and training of graph neural networks. It offers a wide range of tools and functionalities to work efficiently with graph-structured data. PyTorch is what you use to build and train regular neural networks. PyTorch Geometric builds on top of PyTorch. Let's look at some features of PyG. PyTorch Geometric provides easy-to-use data structures for representing graphs, along with utilities for loading and processing common graph data sets. PyG supports a wide range of GNN layers. The library includes a variety of pre-implemented layers such as graph convolutional networks, graph attention networks, and more, allowing us to build and experiment with complex GNN architectures easily. PyG is optimized for high…

Contents