Metadata-Version: 2.1
Name: schnetpack
Version: 2.0.4
Summary: SchNetPack - Deep Neural Networks for Atomistic Systems
Home-page: https://github.com/atomistic-machine-learning/schnetpack
Author: Kristof T. Schuett, Michael Gastegger, Stefaan Hessmann, Niklas Gebauer, Jonas Lederer
License: MIT
Requires-Python: >=3.6
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: sympy
Requires-Dist: ase>=3.21
Requires-Dist: h5py
Requires-Dist: pyyaml
Requires-Dist: hydra-core>=1.1.0
Requires-Dist: torch>=1.9
Requires-Dist: pytorch_lightning>=2.0.0
Requires-Dist: torchmetrics==1.0.1
Requires-Dist: hydra-colorlog>=1.1.0
Requires-Dist: rich
Requires-Dist: fasteners
Requires-Dist: dirsync
Requires-Dist: torch-ema
Requires-Dist: matscipy
Requires-Dist: tensorboard
Provides-Extra: test
Requires-Dist: pytest; extra == "test"
Requires-Dist: pytest-datadir; extra == "test"
Requires-Dist: pytest-benchmark; extra == "test"


        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
