SchNetPack is a ready-to-use 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.

SchNetPack aims to provide accessible atomistic neural networks that can be trained and applied out-of-the-box, while still being extensible to custom atomistic architectures.

SchNetpack 1.0 will be soon available on github coming with an exhaustive documentation.

For further information the preprint version of our paper SchNetPack: A Deep Learning Toolbox For Atomistic Systems is already available on the arXiv and will soon be published on the JCTC Journal.