This repository contains the code to the paper. The code trains four different machine learning models for the prediction of polymer properties. Two of the models are single-task (nn_st.py and gpr.py) and two are multi-task (nn_mt2.py and nn_mt.py) models. Please see the paper for more details.
Clone repo
git clone https://gitlab.com/ramprasad-group/multi-task-learning && cd multi-task-learning
Init poetry
poetry install
poetry shell
cd .. && mkdir test && cd test
Run
mtask -h
mkdir dataset && cd dataset
Place dataset in the dataset/
directory
Run
mtask_new nn-st train
or
mtask_new nn-mt train
or
mtask_new nn-st2 train