{"id":14958669,"url":"https://github.com/tjwei/ganotebooks","last_synced_at":"2025-05-16T13:03:36.134Z","repository":{"id":37390780,"uuid":"76036762","full_name":"tjwei/GANotebooks","owner":"tjwei","description":"wgan, wgan2(improved, gp), infogan, and dcgan implementation in  lasagne, keras, pytorch","archived":false,"fork":false,"pushed_at":"2018-02-11T07:24:06.000Z","size":257520,"stargazers_count":1498,"open_issues_count":11,"forks_count":370,"subscribers_count":98,"default_branch":"master","last_synced_at":"2025-04-09T08:05:04.298Z","etag":null,"topics":["cyclegan","dcgan","dragan","infogan","keras","lasagne","pix2pix","pytorch","tensorflow","wgan","wgan-gp"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tjwei.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":"2016-12-09T13:15:33.000Z","updated_at":"2025-02-15T14:25:44.000Z","dependencies_parsed_at":"2022-07-20T12:02:39.002Z","dependency_job_id":null,"html_url":"https://github.com/tjwei/GANotebooks","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/tjwei%2FGANotebooks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tjwei%2FGANotebooks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tjwei%2FGANotebooks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tjwei%2FGANotebooks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tjwei","download_url":"https://codeload.github.com/tjwei/GANotebooks/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254535826,"owners_count":22087398,"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":["cyclegan","dcgan","dragan","infogan","keras","lasagne","pix2pix","pytorch","tensorflow","wgan","wgan-gp"],"created_at":"2024-09-24T13:17:47.690Z","updated_at":"2025-05-16T13:03:36.114Z","avatar_url":"https://github.com/tjwei.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Generative Adversarial Notebooks\n## Collection of my Generative Adversarial Network implementations\n\nMost codes are for python3, most notebooks works on \n\n### CycleGAN\n* CycleGAN-lasagne\n* CycleGAN-keras\n\n### CycleGAN results\n\u003cimg src=\"img/cyclegan_58_11603.png\" height=300 /\u003e \nResult after 3 hours and 58 epochs on a GTX 1080. From top to bottom: Input, Fake, Recreate of the input.\n\n\u003cimg src=\"img/cyclegan_face.png\" height=300 /\u003e \nFace-off result. From top to bottom: Input, Fake, Recreate of the input.\n[youtube video](https://www.youtube.com/watch?v=Fea4kZq0oFQ)\n\n### pix2pix\n* pix2pix-keras: pix2pix GAN Keras implementation\n* pix2pix-lasagne: pix2pix GAN Lasagne implementation\n* pix2pix-torch: pix2pix GAN pytorch implementation\n\n### pix2pix sample results\n\u003cimg src=\"img/pix2pix.png\" height=\"200\" /\u003e\nValidation result of edges-to-shoes after 12 epochs. From top to bottom: Input, Ground truth, the result.\n\u003cimg src=\"img/pix2pix_resnet.png\" height=\"200\" /\u003e\nValidation result of  facades dataset after 150 epochs using resnet. From top to bottom: Input, Ground truth, the result.\n\n\n### WGAN on CIFAR10\n* wgan-keras: Wasserstein GAN  Keras implementation\n* wgan-lasagne: Wasserstein GAN Lasagne implementation\n* wgan-torch: Wasserstein GAN pytorch implementation based on https://github.com/martinarjovsky/WassersteinGAN\n\n### WGAN2 (improved WGAN/WGAN-gp)\n* wgan2-lasagne:  improved WGAN Lasagne implementation (on CIFAR10)\n* wgan2-keras: improved WGAN Keras implementation (on CIFAR10)\n* wgan2-lasagne-anime: WGAN on anime face images, lasagne \n* wgan2-AC-lasagne:  improved WGAN Lasagne implementation with Auxillary classfier\n### WGAN2 sample results\n* cifar10 dataset\n\n\u003cimg src=\"img/wgan2-cifar10.png\" height=\"100\" /\u003e\n\n* cifar10 dataset with Auxillary classfier\n\n\u003cimg src=\"img/wgan2-ac-cifar10.png\" height=\"400\" /\u003e\n\n\n* anime face dataset\n\n\u003cimg src=\"img/wgan2-anime.png\" height=\"500\" /\u003e\n\n\n\n\n### InfoGAN \n* mnist-infogan: InfoGAN Lasagne on MNIST dataset\n* mnist-infogan-paper-uniform: InfoGAN Lasagne on MNIST dataset (fllowing the paper implementation)\n### InfoGAN sample results\n\u003cimg src=\"img/infogan-mnist.png\" height=\"300\" /\u003e\n\n\n### DCGAN\n* dcgan-lasagne: DCGAN in Lasagne\n### DCGAN sample results\n\u003cimg src=\"img/dcgan-cifar10.png\" height=\"300\" /\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftjwei%2Fganotebooks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftjwei%2Fganotebooks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftjwei%2Fganotebooks/lists"}