{"id":32141149,"url":"https://github.com/sandiamlminiapps/minigan","last_synced_at":"2026-02-25T20:02:54.109Z","repository":{"id":56825580,"uuid":"242194680","full_name":"SandiaMLMiniApps/miniGAN","owner":"SandiaMLMiniApps","description":"A GAN Proxy App","archived":false,"fork":false,"pushed_at":"2020-09-14T23:15:10.000Z","size":23,"stargazers_count":2,"open_issues_count":1,"forks_count":3,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-12-07T06:53:41.466Z","etag":null,"topics":["mini-apps","snl-mini-apps"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SandiaMLMiniApps.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-02-21T17:29:06.000Z","updated_at":"2025-01-22T18:32:29.000Z","dependencies_parsed_at":"2022-09-13T08:12:10.828Z","dependency_job_id":null,"html_url":"https://github.com/SandiaMLMiniApps/miniGAN","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/SandiaMLMiniApps/miniGAN","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SandiaMLMiniApps%2FminiGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SandiaMLMiniApps%2FminiGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SandiaMLMiniApps%2FminiGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SandiaMLMiniApps%2FminiGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SandiaMLMiniApps","download_url":"https://codeload.github.com/SandiaMLMiniApps/miniGAN/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SandiaMLMiniApps%2FminiGAN/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29837453,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-25T19:08:47.527Z","status":"ssl_error","status_checked_at":"2026-02-25T18:59:04.705Z","response_time":61,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["mini-apps","snl-mini-apps"],"created_at":"2025-10-21T06:09:03.191Z","updated_at":"2026-02-25T20:02:54.104Z","avatar_url":"https://github.com/SandiaMLMiniApps.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# miniGAN\n\nminiGAN is a generative adversarial network code developed as part of the \nExascale Computing Project's (ECP) [ExaLearn](https://www.exascaleproject.org/project/exalearn-co-design-center-for-exascale-machine-learning-technologies/) \nproject at Sandia National Laboratories.\n\nminiGAN v. 1.0.0\n\nFor questions, contact J. Austin Ellis (johelli@sandia.gov) or Siva Rajamanickam (srajama@sandia.gov).\n\n------------------------------------------------\nDescription:\n------------------------------------------------\n\nminiGAN is a proxy application for generative adversarial networks.\n\nThe objective of the miniGAN miniapp is to model performance for training \ngenerator and discriminator networks.\nThe GAN's generator and discriminator generate plausible 2D/3D maps and identify fake maps, respectively. \nRelated applications exist in cosmology (CosmoGAN, ExaGAN) and wind energy (ExaWind).\n\nAuthors: J. Austin Ellis (johelli@sandia.gov) and Siva Rajamanickam (srajama@sandia.gov)\n\n------------------------------------------------\nBenchmarks:\n------------------------------------------------\nComing soon.\n\n------------------------------------------------\nTo Install:\n------------------------------------------------\n\n### Model/Package Combos\n\n#### Pytorch Tested\n- python/3.5.2\n- pytorch/1.3.1\n- horovod/0.18.2\n\n### Install\n\n1. Enter desired pytorch directory and prepare python env\n  + Run `./setup_python_env.sh`\n  + Run `source ./minigan_torch_env/bin/activate` (for pytorch)\n  + (Run `deactivate` to exit python env)\n\n2. Generate bird dataset\n  + Move to ${minigan_dir}/data \n  + Run `python generate_random_images.py --help` for running options\n\n3. Run `python3 minigan_driver.py --help` for running options \n  + Default dataset is \"random\". Switch to \"--dataset bird\" to use generated dataset.\n\n4. Run!\n\n### OLCF Summit instructions\n\n1. Do not run `setup_python_env.sh`, instead run `module load ibm-wml-ce/1.7.0-1` to load IBM's Watson ML Community Edition.\n    + This should contain PyTorch, Horovod, Matplotlib \n    + Have not been successful with Summit's standalone pip / anaconda\n2. Obtain an interactive session using\n    + `bsub --nnodes 1 -Is -W 1:00 -P \u003cProjID\u003e /bin/bash`\n3. Run using \n    + `ddlrun python3 minigan_driver.py --dataset bird`\n\n\n### Experimental! \n#### Make use of kokkos-kernels layers/operations\n\n1. In development\n\nPlease report bugs or feature requests to: https://github.com/SandiaMLMiniApps/miniGAN/issues\n\n##### [LICENSE](https://github.com/SandiaMLMiniApps/miniGAN/blob/devel/LICENSE)\n[![License](https://img.shields.io/badge/License-BSD%203--Clause-blue.svg)](https://opensource.org/licenses/BSD-3-Clause)\n\nminiGAN is licensed under standard 3-clause BSD terms of use.  For\nspecifics, please refer to the LICENSE file contained in the\nrepository or distribution.  Under the terms of Contract DE-NA0003525 with NTESS,\nthe U.S. Government retains certain rights in this software.\n\n\n\n\n\n\n\n\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsandiamlminiapps%2Fminigan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsandiamlminiapps%2Fminigan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsandiamlminiapps%2Fminigan/lists"}