{"id":31368391,"url":"https://github.com/dirmeier/wgan-gp","last_synced_at":"2026-06-21T01:31:15.637Z","repository":{"id":311051589,"uuid":"905723561","full_name":"dirmeier/wgan-gp","owner":"dirmeier","description":"      A Wasserstein GAN with gradient penalty in Flax/NNX","archived":false,"fork":false,"pushed_at":"2025-08-21T19:27:55.000Z","size":558,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-06-21T01:31:11.342Z","etag":null,"topics":["flax","jax","python","wgan-gp"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dirmeier.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-12-19T11:53:12.000Z","updated_at":"2025-10-24T11:09:29.000Z","dependencies_parsed_at":"2025-08-21T21:55:29.686Z","dependency_job_id":"a9feeabf-2ff8-4c80-92fd-9fca11ff9f0a","html_url":"https://github.com/dirmeier/wgan-gp","commit_stats":null,"previous_names":["dirmeier/wgan-gp"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/dirmeier/wgan-gp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dirmeier%2Fwgan-gp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dirmeier%2Fwgan-gp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dirmeier%2Fwgan-gp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dirmeier%2Fwgan-gp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dirmeier","download_url":"https://codeload.github.com/dirmeier/wgan-gp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dirmeier%2Fwgan-gp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34591166,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-20T02:00:06.407Z","response_time":98,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["flax","jax","python","wgan-gp"],"created_at":"2025-09-27T16:10:03.997Z","updated_at":"2026-06-21T01:31:15.619Z","avatar_url":"https://github.com/dirmeier.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# WGAN-GP\n\n[![ci](https://github.com/dirmeier/wgan-gp/actions/workflows/ci.yaml/badge.svg)](https://github.com/dirmeier/wgan/actions/workflows/ci.yaml)\n\n## About\n\nThis repository implements the [Wasserstein GAN with gradient penalty](https://arxiv.org/abs/1704.00028) loss for testing.\nThe implementations are in JAX and Flax/NNX.\n\n## Example usage\n\nAn experiment where we train a WGAN-GP on MNIST can be found in [`experiments/mnist/`](experiments/mnist/).\nTo run the example, first download the latest release and install all dependencies via:\n\n```bash\nwget -qO- https://github.com/dirmeier/wgan-gp/archive/refs/tags/\u003cTAG\u003e.tar.gz | tar zxvf -\nuv sync --all-groups\n```\n\nTo train a model and make visualizations, call:\n\n```bash\ncd experiments/eight_gaussians_two_moons\npython main.py\n```\n\nBelow are the results from training the GN using the hyperparameters defined in [`experiments/mnist/config.py`](experiments/mnist/config.py).\nA sample after training 20k steps (i.e., gradient steps) is shown below.\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"experiments/mnist/figures/samples.png\" width=\"700\"\u003e\n\u003c/div\u003e\n\n## Installation\n\nTo install the latest GitHub \u003cRELEASE\u003e, just call the following on the\ncommand line:\n\n```bash\npip install git+https://github.com/dirmeier/wgan@\u003cTAG\u003e\n```\n\n## Author\n\nSimon Dirmeier \u003ca href=\"mailto:simd23@pm.me\"\u003esimd23 @ pm dot me\u003c/a\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdirmeier%2Fwgan-gp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdirmeier%2Fwgan-gp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdirmeier%2Fwgan-gp/lists"}