Spatial Link Prediction

This project is based on the Lightning-Hydra-Template. See template docs for more information.

Description

This repository contains the code for the experiments in our paper Spatial Link Prediction: Learning topological relationships in MEP systems.

How to run

This code was developed and tested with Python 3.9.15, PyTorch 1.13, and torch-geometric 2.2.0.

Install dependencies

# clone project
git clone https://github.com/RWTH-E3D/SpatialLinkPrediction
cd SpatialLinkPrediction

# [OPTIONAL] create conda environment
conda create -n myenv python=3.9
conda activate myenv

# install pytorch 1.13 according to instructions
# https://pytorch.org/get-started/
# For Linux and Windows
conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.7 -c pytorch -c nvidia

# install torch-geometric
conda install pyg -c pyg

# install other requirements
pip install -r requirements.txt

Train model with chosen experiment configuration from configs/experiment/

python src/train.py experiment=experiment_name.yaml

You can override any parameter from command line like this

python src/train.py experiment=experiment_name.yaml trainer.max_epochs=20 datamodule.batch_size=64