https://github.com/imperialcollegelondon/ipwgan

https://github.com/imperialcollegelondon/ipwgan

Science Score: 26.0%

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

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
    Found 1 DOI reference(s) in README
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (5.4%) to scientific vocabulary
Last synced: 4 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: ImperialCollegeLondon
  • Language: Python
  • Default Branch: main
  • Size: 170 KB
Statistics
  • Stars: 7
  • Watchers: 2
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Created over 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme

README.md

IPWGAN

Here is a Code of IPWGAN- Improved Pymarid Wasserstein Generative Adversarial Network Figure IPWGAN, Improved Pyramid Wasserstein Generative Adversarial Network, use to generate complex porous media.

Features

  • Feature 1: add pyramid structure generator to capture multiscale characterization
  • Feature 2: add Feature Statistics Mixing Regularization to control the process of training
  • Feature 3: add -LP to control training process.

Usage

Create dataset: python createtrainingimagess.py --image D:\fw3L.tif --name fw3r --target_dir I:\wet255128

Training: python mainWGANFPN.py --dataset 3D --dataroot SAV --imageSize 128 --batchSize 8 --ngf 64 --ndf 16 --nz 512 --niter 1600 --lr 0.00005 --ngpu 1 –cuda

Generation: python generatorWFPNM.py --imageSize 128 --ngf 64 --ndf 16 --nz 512 --netG SAVInetGepochtrain500ppp.pth --experiment nb --imsize 8 –cuda

Paper

Cite as: Linqi Zhu, Branko Bijeljic, Martin Julian Blunt. Generation of Heterogeneous Pore-Space Images Using Improved Pyramid Wasserstein Generative Adversarial Networks. ESS Open Archive . December 03, 2023. DOI: 10.22541/essoar.170158343.30188169/v1

Owner

  • Name: Imperial College London
  • Login: ImperialCollegeLondon
  • Kind: organization
  • Email: icgithub-support@imperial.ac.uk
  • Location: Imperial College London

Imperial College main code repository

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: over 1 year ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels