{"id":20886446,"url":"https://github.com/gsurma/image_generator","last_synced_at":"2025-04-13T10:57:10.103Z","repository":{"id":90787617,"uuid":"166616542","full_name":"gsurma/image_generator","owner":"gsurma","description":"DCGAN image generator 🖼️.","archived":false,"fork":false,"pushed_at":"2021-07-09T08:52:13.000Z","size":18369,"stargazers_count":218,"open_issues_count":3,"forks_count":82,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-03-27T02:11:28.212Z","etag":null,"topics":["dcgan","dcgan-tensorflow","deep-learning","gan","generative-adversarial-network","jupyter","machine-learning","neural-network","python","python3","simpsons","simpsons-dataset","tensorflow"],"latest_commit_sha":null,"homepage":"https://gsurma.github.io","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/gsurma.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null},"funding":{"patreon":"gsurma"}},"created_at":"2019-01-20T02:48:34.000Z","updated_at":"2025-01-07T15:52:24.000Z","dependencies_parsed_at":null,"dependency_job_id":"1ef0836e-da72-4d7b-a63e-c4fb5564bc06","html_url":"https://github.com/gsurma/image_generator","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/gsurma%2Fimage_generator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gsurma%2Fimage_generator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gsurma%2Fimage_generator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gsurma%2Fimage_generator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gsurma","download_url":"https://codeload.github.com/gsurma/image_generator/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248703195,"owners_count":21148117,"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":["dcgan","dcgan-tensorflow","deep-learning","gan","generative-adversarial-network","jupyter","machine-learning","neural-network","python","python3","simpsons","simpsons-dataset","tensorflow"],"created_at":"2024-11-18T08:16:58.457Z","updated_at":"2025-04-13T10:57:10.079Z","avatar_url":"https://github.com/gsurma.png","language":"Jupyter Notebook","funding_links":["https://patreon.com/gsurma"],"categories":[],"sub_categories":[],"readme":"\u003ch3 align=\"center\"\u003e\n  \u003cimg src=\"assets/image_generator_icon_web.png\" width=\"300\"\u003e\n\u003c/h3\u003e\n\n# Image Generator\n\nPython notebook containing TensorFlow DCGAN implementation. It was trained on a [Simpsons Faces](https://www.kaggle.com/kostastokis/simpsons-faces) dataset.\n\n\u003cbr\u003e\n\nCheck out corresponding Kaggle kernel: [Image Generator](https://www.kaggle.com/greg115/image-generator-dcgan-the-simpsons-dataset).\n\nCheck out corresponding Medium article:\n\n[Image Generator - Drawing Cartoons with Generative Adversarial Networks](https://towardsdatascience.com/image-generator-drawing-cartoons-with-generative-adversarial-networks-45e814ca9b6b)\n\n\u003ch3 align=\"center\"\u003e\n  \u003cimg src=\"assets/homer.gif\"\u003e\n\u003c/h3\u003e\n\n## DCGAN\nNetwork architecture by [Radford et al., 2015](https://arxiv.org/abs/1511.06434).\n\u003cimg src=\"assets/model.png\"\u003e\n\n## Training\nVisualization of training with the following hyperparameteres.\n\u003cimg src=\"assets/epochs.gif\"\u003e\n\n\tIMAGE_SIZE = 128\n\tNOISE_SIZE = 100\n\tLR_D = 0.00004\n\tLR_G = 0.0004\n\tBATCH_SIZE = 64\n\tEPOCHS = 300\n\tBETA1 = 0.5\n\tWEIGHT_INIT_STDDEV = 0.02\n\tEPSILON = 0.00005\n\n\n## Results\n\nCherry-picked generated samples.\n\n\u003cimg src=\"assets/final_grid.png\"\u003e\n\n\nAs expected, there were some funny-looking malformed faces as well.\n\u003cimg src=\"assets/misc.png\"\u003e\n\n## Author\n\n**Greg (Grzegorz) Surma**\n\n[**PORTFOLIO**](https://gsurma.github.io)\n\n[**GITHUB**](https://github.com/gsurma)\n\n[**BLOG**](https://medium.com/@gsurma)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgsurma%2Fimage_generator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgsurma%2Fimage_generator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgsurma%2Fimage_generator/lists"}