{"id":23935141,"url":"https://github.com/osh/kerasgan","last_synced_at":"2025-04-05T20:06:32.709Z","repository":{"id":141758967,"uuid":"62264943","full_name":"osh/KerasGAN","owner":"osh","description":"A couple of simple GANs in Keras","archived":false,"fork":false,"pushed_at":"2018-03-22T04:42:48.000Z","size":2557,"stargazers_count":501,"open_issues_count":12,"forks_count":177,"subscribers_count":26,"default_branch":"master","last_synced_at":"2025-03-29T19:04:06.562Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/osh.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2016-06-29T23:41:34.000Z","updated_at":"2024-11-10T18:17:45.000Z","dependencies_parsed_at":null,"dependency_job_id":"484d3d03-cc55-4aaf-b05f-bf7145c34f84","html_url":"https://github.com/osh/KerasGAN","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/osh%2FKerasGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/osh%2FKerasGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/osh%2FKerasGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/osh%2FKerasGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/osh","download_url":"https://codeload.github.com/osh/KerasGAN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247393569,"owners_count":20931812,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":[],"created_at":"2025-01-06T00:44:44.936Z","updated_at":"2025-04-05T20:06:32.663Z","avatar_url":"https://github.com/osh.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# WARNING!!!!\n\n**This repository is not maintained!**\nI highly recommend you use a better maintained and up to date library such as: https://github.com/eriklindernoren/Keras-GAN\n\n------\n\n# KerasGAN\nThis module includes a GAN implementation in Keras for the MNIST data set\nSee full article @ https://oshearesearch.com/index.php/2016/07/01/mnist-generative-adversarial-model-in-keras/\n\n# GAN Overview\nThe GAN includes a generative and discrimintive network defined in Keras' functional API, they can then be chained together to make a composite model for training end-to-end.\n![GAN BlockDiag](https://oshearesearch.com/wp-content/uploads/2016/07/mnist_gan.png)\n\n# Generated Images\nGenerated Images aren't perfect, the network is still pretty small and additional tuning would likely help.\n![Generated Digits](https://oshearesearch.com/wp-content/uploads/2016/07/mnist_gan7-300x300.png)\n\n# Learning Rates\nI tend to find the having a larger (faster) learning rate on the discrimintive model leads to better results than keeping them equal in the discriminitive and generative training tasks. \nWould be curious to hear from others who are familiar with GAN tuning here.\nWhen training with imbalanced learning rates like this, discriminitive loss stays pretty low, and the discriminitive model generally stays ahead of discriminatring new strange represenentations from the generative model.\n![Training Loss](https://oshearesearch.com/wp-content/uploads/2016/07/mnist_gan_loss4.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fosh%2Fkerasgan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fosh%2Fkerasgan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fosh%2Fkerasgan/lists"}