Data

Tools

Indexes

Applications

Experiments

Open Source Science

maxwell-interface-updater

https://github.com/2beers1218/maxwell-interface-updater

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 1 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (12.5%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: 2Beers1218
  • License: lgpl-2.1
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 15.1 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 1
Created over 3 years ago · Last pushed 12 months ago
Metadata Files
Readme License Citation

README.md

KirasFM-NN: KirasFM + Feedforawrd Neural Network

This repository consists of a modified version of the Maxwell Solver KirasFM, framework built on top of deal.II that provides all necessary tools for solving time-harmonic Maxwell's equations with an optimized Schwarz method and a feedforward neural network-enhanced that is used to compute an approximation of the surface operator that is used in the optimized Schwarz method.

Citation

Please use the Cite this repository button in the About section of this repository.

DOI

Installation - Dependencies

The dependencies required are deal.II, PyTorch, and Jupyter Lab. In the following, it is assumed that a recent C++ compiler (e.g., GCC) and a recent Python version are installed.

Obtaining deal.II

This is a CMake script that installs dea.lII along with its dependencies. And it should be the easiest way to install deal.II with all its dependencies. For more details, see https://github.com/kinnewig/dcs2.

tl;dr: 1. Step: Download dcs2: git clone https://github.com/kinnewig/dcs2.git cd dcs2 2. Step: Run the install script: ./dcs.sh -b </path/to/build> -p </path/to/install>

Remember to replace </path/to/build> with the path where you would like to store the temporary files created while installing deal.II (the folder can be deleted once you successfully installed deal.II).

Also, remember to replace </path/to/install> with the folder where you would like to install deal.II.

If you have any problems feel free to open an issue on: https://github.com/kinnewig/dcs2/issues

(Optional) Create a venv:

Before you begin with installing the required Python packages, it is recommended to create a venv (virtual environment) python -m venv </path/to/new/virtual/environment> Remember to replace </path/to/new/virtual/environment> with the path where you would like to store the venv.

After creating the venv, you can enter the venv by . .</path/to/new/virtual/environment>/bin/activate

For more details on venv, see: https://docs.python.org/3/library/venv.html

Install PyTourch

To install PyTorch with the CPU backend, use pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu

For more details on PyTorch see https://pytorch.org/get-started/locally/

Install Jupyter Lab

To install Jupyter Lab, use pip3 install jupyterlab

Jupyter Lab can be started by jupyter lab After that, Jupyter Lab should open in the browser.

Owner

  • Login: 2Beers1218
  • Kind: user

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: KirasFM-NN
message: >-
  Domain Decomposition with Neural Network Interface
  Approximations for time-harmonic Maxwell's equations with
  different wave numbers
type: software
authors:
  - given-names: Tobias
    family-names: Knoke
    email: knoke@ifam.uni-hannover.de
    affiliation: >-
      Institute of Applied Mathematics, Leibniz University
      Hannover
    orcid: 'https://orcid.org/0000-0003-2987-5110'
  - given-names: Sebastian
    family-names: Kinnewig
    email: kinnewig@ifam.uni-hannover.de
    affiliation: >-
      Institute of Applied Mathematics, Leibniz University
      Hannover
    orcid: 'https://orcid.org/0000-0002-0923-7413'
identifiers:
  - type: doi
    value: 10.17268/sel.mat.2023.01.01
    description: >-
      Domain Decomposition with Neural Network Interface
      Approximations for time-harmonic Maxwell’s equations
      with different wave numbers
  - type: doi
    value: 10.5281/zenodo.13837201
    description: KirasFM-NN release version 1.0.0
repository-code: 'https://github.com/2Beers1218/Maxwell-interface-updater'
abstract: >-
  This repository consists of a modified version of the
  Maxwell Solver KirasFM, which is based on a fixed-point
  domain decomposition method and a feedforward neural
  network-enhanced that is used to compute an approximation
  of the surface operator occurring in the fixed point
  formulation of the Maxwell equation. 
keywords:
  - Maxwell's equations
  - Domain Decomposition Method
  - Neural Network
  - Finite Element Method
license: LGPL-2.1
commit: d8b9426cf97a2b74116b670191371a32fa3365f4
version: 1.0.0
date-released: '2024-09-25'

GitHub Events

Total
  • Push event: 2
Last Year
  • Push event: 2