fortnet-ase provides an interface between the neural network implementation Fortnet and the Atomic Simulation Environment (ASE). The calculator employs Fortnet as a prediction engine for the total energy of a system as well as the calculation of atomic forces, e.g. for geometry optimizations and molecular dynamics.
Please note, that this package has been tested for Python 3.X support. Its usage additionally requires
- Atomic Simulation Environment (ase)
- Fortnet Python tools (fortnet-python)
as well as the pytest framework in order to run the regression tests.
First, make sure you have an up-to-date version of pip installed:
python -m pip install --upgrade pip
The package can be downloaded and installed via pip into the active Python interpreter (preferably using a virtual python environment) by
pip install fortnet-ase
or into the user space issueing:
pip install --user fortnet-ase
Alternatively, you can install it locally from source, i.e. from the root folder of the project:
python -m pip install .
Consult following resources for documentation:
New features, bug fixes, documentation, tutorial examples and code testing is welcome during the ongoing fortnet-ase development!
The project is hosted on github. Please check CONTRIBUTING.rst for guide lines.
I am looking forward to your pull request!
fortnet-ase is released under the BSD 2-clause license. See the included LICENSE file for the detailed licensing conditions.