graph-pesΒΆ
Date: Apr 22, 2025 - Author: John Gardner - Version: 0.1.0
graph-pes
is a package designed to accelerate the development of machine-learned potential energy surfaces (ML-PESs) that act on graph representations of atomic structures.
The core component of graph-pes
is the GraphPESModel
.
You can take any model that inherits from this class and:
train and/or fine-tune it on your own data using the
graph-pes-train
command line tool
We provide many GraphPESModel
s, including:
re-implementations of popular architectures, including
NequIP
,PaiNN
,MACE
andTensorNet
wrappers for other popular ML-PES frameworks, including mace-torch, mattersim, and orb-models, that convert their models into
graph-pes
compatibleGraphPESModel
instances
Use graph-pes
to train models from scratch, experiment with new architectures, write architecture-agnostic validation pipelines, and try out different foundation models with minimal code changes.
Useful links:
Train an existing architecture from scratch
Analyse a trained model
Fine-tune a foundation model on your data
Implement your own ML-PES architecture
Define a custom training loop
Learn more about the properties of PESs
Installation:
Install graph-pes
using pip. We recommend doing this in a new environment (e.g. using conda):
conda create -n graph-pes python=3.10 -y
conda activate graph-pes
pip install graph-pes
Please see the GitHub repository for the source code and to report issues.