Skip to content

Latest commit

 

History

History
16 lines (8 loc) · 650 Bytes

README.org

File metadata and controls

16 lines (8 loc) · 650 Bytes

SingleNN

To use this package, please make sure you have PyTorch, NumPy and C++ compiler installed.

The codes are included in the src directory and tutorial.org shows an example using this package. Before using the package, make sure to enter the SimpleNN directory and run

python libsymf_builder.py

This will build a Python-C++ interface that uses the codes from SIMPLE-NN to generate fingerprints.

A. Lee, D. Yoo, W. Jeong, S. Han, SIMPLE-NN: An efficient package for training and executing neural-network interatomic potentials, Computer Physics Communications (2019), https://doi.org/10.1016/j.cpc.2019.04.014.