SchNetPack documentation

SchNetPack is a toolbox for the development and application of deep neural networks to the prediction of potential energy surfaces and other quantum-chemical properties of molecules and materials. It contains basic building blocks of atomistic neural networks, manages their training and provides simple access to common benchmark datasets. This allows for an easy implementation and evaluation of new models.

Contents

Get Started

• Installation
• Training your first models

User guide

• Overview
• Configuration and CLI
• Running MD simulations with the CLI

Tutorials

• Preparing and loading your data
• Training a neural network on QM9
• Training a model on forces and energies
• Molecular dynamics in SchNetPack
• Force Fields for Materials

How-To

• Batch-wise Structure Relaxation
• LAMMPS Interface

Reference

• schnetpack
• schnetpack.atomistic
• schnetpack.data
• schnetpack.datasets
• schnetpack.task
• schnetpack.model
• schnetpack.representation
• schnetpack.nn
• schnetpack.train
• schnetpack.transform
• schnetpack.md