Software Open Access
miniff -- A minimal implementation of classical and neural-network force fields in python
Artem Pulkin;
Niket Agrawal;
André Melo
Other(s)
Slava Ostroukh; Anastasiia Varentcovaminiff 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
(262.5 kB)
| Name | Size | |
|---|---|---|
|
miniff-master.zip
md5:ebc578888019f553622033027db71c76 |
262.5 kB | Download |
43
3
views
downloads
| All versions | This version | |
|---|---|---|
| Views | 43 | 43 |
| Downloads | 3 | 3 |
| Data volume | 787.4 kB | 787.4 kB |
| Unique views | 36 | 36 |
| Unique downloads | 3 | 3 |
Indexed in
- Publication date:
- April 7, 2021
- DOI:
-
- Keyword(s):
- classical force field neural network torch python
- License (for files):
- BSD 2-Clause "Simplified" License