#
# CDDL HEADER START
#
# The contents of this file are subject to the terms of the Common Development
# and Distribution License Version 1.0 (the "License").
#
# You can obtain a copy of the license at
# http://www.opensource.org/licenses/CDDL-1.0.  See the License for the
# specific language governing permissions and limitations under the License.
#
# When distributing Covered Code, include this CDDL HEADER in each file and
# include the License file in a prominent location with the name LICENSE.CDDL.
# If applicable, add the following below this CDDL HEADER, with the fields
# enclosed by brackets "[]" replaced with your own identifying information:
#
# Portions Copyright (c) [yyyy] [name of copyright owner]. All rights reserved.
#
# CDDL HEADER END
#

#
# Copyright (c) 2018--2019, PANNAdevs group.
# All rights reserved.
#
# Contributors:
#    Emine Kucukbenli
#    Franco Pellegrini
#    Ryan S. Elliott
#


This directory contains the Model Driver for potential models generated with 
PANNA package version 1.0.0. The model driver is written in C++.


PANNA is a package of tools for training and validating neural network 
potentials. The underlying machine learning engine is TensorFlow. 
It can be downladed from here:
https://gitlab.com/PANNAdevs/panna
The documentation, related references and how to cite 
can be found in the git repository.


Potentials generated with PANNA can be exported using the following script in
the PANNA package itself:
extract_weights.py 


This tool creates following files that are necessary to export the model 
to KIM:
-A text file which holds the neural network architecture details
-One binary file for each species which holds the weights and biases.
In addition to these files, you will need a CMakeLists.txt file, 
as per usual KIM usage. (see KIM user guide for more information)


This version of the model driver supports the following features:
-Modified Behler Parrinello descriptors
-Gaussian, ReLU and linear activations.
For all other types of neural networks that can be generated with PANNA 
please contact the development team:
https://groups.google.com/d/forum/pannausers