Giter Site home page Giter Site logo

chemshift / fitsnap Goto Github PK

View Code? Open in Web Editor NEW

This project forked from fitsnap/fitsnap

0.0 0.0 0.0 184.92 MB

Software for generating SNAP machine-learning interatomic potentials

License: GNU General Public License v2.0

Shell 0.49% Python 94.85% Cython 4.45% C 0.21%

fitsnap's Introduction

FitSNAP3

A Python Package For Training SNAP Interatomic Potentials for use in the LAMMPS molecular dynamics package

Copyright (2016) Sandia Corporation. Under the terms of Contract DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains certain rights in this software. This software is distributed under the GNU General Public License

Original author:

Aidan P. Thompson, athomps (at) sandia (dot) gov (Sandia National Labs)
http://www.cs.sandia.gov/~athomps

Key contributors (alphabetical):

Mary Alice Cusentino (Sandia National Labs)
Nicholas Lubbers (Los Alamos National Lab)
Charles Sievers (UC Davis, Sandia National Labs)
Adam Stephens (Sandia National Labs)
Mitchell Wood (Sandia National Labs)

Additional authors (alphabetical):

Elizabeth Decolvenaere (D. E. Shaw Research)
Stan Moore (Sandia National Labs)
Steve Plimpton (Sandia National Labs)
Gary Saavedra (Sandia National Labs)
Peter Schultz (Sandia National Labs)
Laura Swiler (Sandia National Labs)

Using this package:

  • [Required] This package expects a python 3.6+ version.
  • [Required] Compile LAMMPS (lammps.sandia.gov) as a shared library, detailed instructions can be found here docs/LAMMPS.md. If you can open python and run import lammps; lmp = lammps.lammps() and it succeeds, you should be good.
  • [Optional] (Required for atomic cluster expansion, ACE, capabilities ) Along with compiling LAMMPS with all of the typical FitSNAP flags, turn the ML-PACE package on.
    • Clone the ML-PACE package with the implemented ACE descriptor computes into your build directory from: [email protected]:jmgoff/lammps-user-pace.git
    • Follow the README.md and INSTALL.md in this repo to build lammps with ACE descriptor calculators

Installing:

  • For the most recent bug fixes/code changes:
    • Clone this repository and add it to your PYTHONPATH environment variable. Periodically git pull for code updates.
  • A minimal working environment can be achieved with the following; conda create -n fitsnap python=3.9 ; conda activate fitsnap ; conda install lammps psutil pandas tabulate mpi4py
  • NOTE : Conda lammps installation does NOT include ACE descriptor set or SPIN package needed for these corresponding examples. If the conda install of lammps fails, run conda config --add channels conda-forge and retry.
  • See docs/INSTALL.md for more information.

Running:

  • (mpirun -np #) python -m fitsnap3 [options] infile (optional)
  • Command line options can be seen with python -m fitsnap3 -h
  • Input files are described by docs/TEMPLATE.in and docs/GROUPLIST.template
  • Examples of published SNAP interatomic potentials can be found in examples/

fitsnap's People

Contributors

athomps avatar carlos-pereyra avatar charlessievers avatar chemshift avatar cusentino avatar jan-janssen avatar jmgoff avatar ldwillia avatar megmcca avatar mitwood avatar rohskopf avatar snikolov3 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.