Commit a56b7ed5 authored by Emine Kucukbenli's avatar Emine Kucukbenli

All PANNA related modules.

parent 7c9c46c2
Pipeline #4764 failed with stage
in 39 seconds
......@@ -127,5 +127,10 @@ Below is a list of the modules developed directly within the context of the pilo
./modules/FFTXlib/readme
./modules/W90_cube_format_non-orthogonal/readme
./modules/miniPWPP/readme
./modules/PANNA-GVECT/readme
./modules/PANNA-TFR/readme
./modules/PANNA-TRAIN/readme
./modules/PANNA-EVAL/readme
./modules/PANNA-Charges/readme
.. _E-CAM: https://www.e-cam2020.eu/
########
PANNA-Charges
########
.. sidebar:: Software Technical Information
Language
Python 3.6.
Documentation Tool
Sphinx,ReStructuredText
Application Documentation
`Doc mirror <https://gitlab.com/PANNAdevs/panna/tree/master/doc>`_
Relevant Training Material
See usage examples in the ``doc/tutorial`` directory of the source code.
Licence
The MIT License (MIT)
.. contents:: :local:
Purpose of Module
___________________
PANNA-Charges module demonstrates how to train a neural network to predict local atomic charges.
This network can later be used to calculat the electrostatic energy density of a crystal.
PANNA-Charge, following other modules within the PANNA project, uses TensorFlow framework.
Features
__________
PANNA-Charge supports periodic and aperiodic structures, multiple species,
and different network architecture for each species.
Building and Testing
______________________________
A stable version of the module can be downloaded using::
XXX
Current installation and testing are done with::
XXX
Here are the commands for installation::
XXX
Test::
XXX
Source Code
___________
To be released soon.
Further Information
______________________
The PANNA-Charges module is developed with the contributions of Y. Shaidu, R. Lot, F. Pellegrini, E. Kucukbenli
########
PANNA-EVAL
########
.. sidebar:: Software Technical Information
Language
Python 3.6.
Documentation Tool
Sphinx,ReStructuredText
Application Documentation
`Doc mirror <https://gitlab.com/PANNAdevs/panna/tree/master/doc>`_
Relevant Training Material
See usage examples in the ``doc/tutorial`` directory of the source code.
Licence
The MIT License (MIT)
.. contents:: :local:
Purpose of Module
___________________
PANNA-EVAL module evaluates an all to all connected neural network
to predict atomistic quantities, e.g. total energy and forces of a given crystal structure.
PANNA-EVAL can be used with other modules of the PANNA project for neural network validation,
but it can also serve to carry the information of the trianed network to other platforms such as
molecular dynamics code LAMMPS.
Although PANNA-EVAL does not need the advanced capabilities of the TensorFlow fraework,
it uses the 'checkpoint' information to automatically test the performance of a network from training data.
Features
__________
coming soon
Building and Testing
______________________________
A stable version of the module can be downloaded using::
XXX
Current installation and testing are done with::
XXX
Here are the commands for installation::
XXX
Test::
XXX
Source Code
___________
To be released soon.
Further Information
______________________
The PANNA-EVAL module is developed with the contributions of R. Lot, Y. Shaidu, F. Pellegrini, E. Kucukbenli
########
PANNA-GVECT
########
.. sidebar:: Software Technical Information
Language
Python 3.6.
Documentation Tool
Sphinx,ReStructuredText
Application Documentation
`Doc mirror <https://gitlab.com/PANNAdevs/panna/tree/master/doc>`_
Relevant Training Material
See usage examples in the ``doc/tutorial`` directory of the source code.
Licence
The MIT License (MIT)
.. contents:: :local:
Purpose of Module
___________________
PANNA-GVECT module demonstrates how to efficiently generate Behler-Parinello and modified Behler-Parinello
descriptors (See References 1,2,3).
These descriptors can then be used in machine learning algorithms. Even though these descriptors were originally designed for
neural network models, they are equally suitable for other supervised learning schemes such as kernel methods,
or unsupervised ones such as clustering techniques.
PANNA-GVECT, unlike other modules within the PANNA project, does not use TensorFlow framework.
Features
__________
PANNA-Gvect supports periodic and aperiodic structures, multiple species,
derivative of the descriptors with respect to atomic positions.
Building and Testing
______________________________
A stable version of the module can be downloaded using::
XXX
Current installation and testing are done with::
XXX
Here are the commands for installation::
XXX
Test::
XXX
Source Code
___________
To be released soon.
Further Information
______________________
The PANNA-GVECT module is developed with the contributions of R. Lot, Y. Shaidu, F. Pellegrini, E. Kucukbenli
########
PANNA-TFR
########
.. sidebar:: Software Technical Information
Language
Python 3.6.
Documentation Tool
Sphinx,ReStructuredText
Application Documentation
`Doc mirror <https://gitlab.com/PANNAdevs/panna/tree/master/doc>`_
Relevant Training Material
See usage examples in the ``doc/tutorial`` directory of the source code.
Licence
The MIT License (MIT)
.. contents:: :local:
Purpose of Module
___________________
PANNA-TFR module demonstrates how to efficiently pack the Behler-Parinello and
modified Behler-Parinello descriptor vectors (See References 1,2,3) written in binary format, into TensorFlow data format
for efficient reading during training.
These descriptors can then be used within TensorFlow efficiently, reducing the overhead during batch creation.
PANNA-TFR is built on TensorFlow.
Features
__________
PANNA-TFR supports descriptors that change size across records, i.e. data points with different number of atoms
are stored efficiently without padding.
Building and Testing
______________________________
A stable version of the module can be downloaded using::
XXX
Current installation and testing are done with::
XXX
Here are the commands for installation::
XXX
Test::
XXX
Source Code
___________
To be released soon.
Further Information
______________________
The PANNA-TFR module is developed with the contributions of R. Lot, Y. Shaidu, F. Pellegrini, E. Kucukbenli
########
PANNA-TRAIN
########
.. sidebar:: Software Technical Information
Language
Python 3.6.
Documentation Tool
Sphinx,ReStructuredText
Application Documentation
`Doc mirror <https://gitlab.com/PANNAdevs/panna/tree/master/doc>`_
Relevant Training Material
See usage examples in the ``doc/tutorial`` directory of the source code.
Licence
The MIT License (MIT)
.. contents:: :local:
Purpose of Module
___________________
PANNA-TRAIN is a neural network training module for atomistic data, eg. prediction of total energy and forces
given a crystal structure.
It implements a separate atomic network for each species, following the seminal work of Behler and Parinello.
(See References 1,2,3)
which can later be used as interatomic potential in molecular dynamics simulations.
PANNA-TRAIN uses TensorFlow framework as the underlying neural network training and data i/o engine.
Features
__________
PANNA-TRAIN supports all to all connected networks for each species.
Networks with different number of nodes and layers are allowed.
It further supports controlling the training dynamics: eg. reeze/unfreeze layers, weight transfer, decaying learning rates etc.
Building and Testing
______________________________
A stable version of the module can be downloaded using::
XXX
Current installation and testing are done with::
XXX
Here are the commands for installation::
XXX
Test::
XXX
Source Code
___________
To be released soon.
Further Information
______________________
The PANNA-TRAIN module is developed with the contributions of R. Lot, Y. Shaidu, F. Pellegrini, E. Kucukbenli
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment