Installation¶

Install Torch Geometric Pool in your graph deep learning pipeline.

Torch Geometric Pool is compatible with Python>=3.9. We recommend installation on a Anaconda or Miniconda environment or a virtual env.

Torch Geometric Pool is conveniently available as a Python package on PyPI and can be easily installed using pip.

pip install torch-geometric-pool

For the latest version, consider installing from source:

pip install git+https://github.com/tgp-team/torch-geometric-pool.git

Before installation

Torch Geometric Pool is built upon PyTorch>=1.8 and PyG>=2.6. Make sure you have both installed in your environment before installation. In the following, we provide instructions on how to install them for the chosen installation procedure.

Installing using conda¶

To install Torch Geometric Pool using conda, clone the repository, navigate to the library root directory and create a new conda environment using the provided conda configuration:

git clone https://github.com/tgp-team/torch-geometric-pool.git
cd torch-geometric-pool
conda env create -f conda_env.yml

Then, activate the environment and install tgp using pip.

conda activate tgp
pip install .

Quickstart¶

Package API

Learn how to configure and build your graph pooling operator.

tgp

Tutorials

Learn how to use tgp at its best.

Tutorials