PyTorch Geometric 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, 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.
In detail, the following methods are currently implemented:
- SplineConv from Fey et al.: SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels (CVPR 2018)
- GCNConv from Kipf and Welling: Semi-Supervised Classification with Graph Convolutional Networks (ICLR 2017)
- ChebConv from Defferrard et al.: Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering (NIPS 2017)
- NNConv adapted from Gilmer et al.: Neural Message Passing for Quantum Chemistry (ICML 2017)
- GATConv from Veličković et al.: Graph Attention Networks (ICLR 2018)
- AGNNProp from Kiran et al.: Attention-based Graph Neural Network for Semi-Supervised Learning
- SAGEConv from Hamilton et al.: Inductive Representation Learning on Large Graphs (NIPS 2017)
- Graclus Pooling from Dhillon et al.: Weighted Graph Cuts without Eigenvectors: A Multilevel Approach (PAMI 2007)
- Voxel Grid Pooling
Head over to our documentation to find more about installation, data handling, creation of datasets and a full list of implemented methods, transforms, and datasets.
For a quick start, check out our provided examples in the examples/ directory.
We are currently in our first alpha release and work on completing documentation. If you notice anything unexpected, please open an issue and let us know. If you are missing a specific method, feel free to open a feature request. We are constantly encouraged to make PyTorch Geometric even better.
If cuda is available, add CUDA to $PATH and $CPATH (note that your actual CUDA path may vary from /usr/local/cuda)
$ PATH=/usr/local/cuda/bin:$PATH
$ echo $PATH
$ CPATH=/usr/local/cuda/install:$CPATH
$ echo $CPATH
and verify that nvcc is accessible from your terminal:
$ nvcc --version
Then install all needed packages:
$ pip install cffi
$ pip install --upgrade torch-scatter
$ pip install --upgrade torch-unique
$ pip install --upgrade torch-cluster
$ pip install --upgrade torch-spline-conv
$ pip install torch-geometric
cd examples
python cora.py
Please cite our paper if you use this code in your own work:
@inproceedings{Fey/etal/2018,
title={{SplineCNN}: Fast Geometric Deep Learning with Continuous {B}-Spline Kernels},
author={Fey, Matthias and Lenssen, Jan Eric and Weichert, Frank and M{\"u}ller, Heinrich},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2018},
}
python setup.py test