Published April 7, 2021
| Version 0.1.3
Software
Open
miniff -- A minimal implementation of classical and neural-network force fields in python
Creators
- 1. QuTech and Kavli Institute of Nanoscience, TU Delft
- 2. Digital Competence Centre, TU Delft
- 3. Kavli Institute of Nanoscience, TU Delft
Contributors
- 1. QuTech, TU Delft
- 2. Kavli Institute of Nanoscience, TU Delft
Description
miniff is a minimal implementation of classical and neural-network force fields written in python. It is based on Behler-Parinello approach to fitting classical atomic energies and uses pytorch and cython under the hood. The package addresses various aspects of neural-network classical potentials, including dataset construction, computing descriptors, assembling workflows, and more. The implementation is parallelized and tested.
Note: this version includes a limited documentation.
Files
miniff-master.zip
Files
(262.5 kB)
Name | Size | Download all |
---|---|---|
md5:ebc578888019f553622033027db71c76
|
262.5 kB | Preview Download |