{"id":20724534,"url":"https://github.com/simoninithomas/catdcgan","last_synced_at":"2025-05-11T17:52:31.528Z","repository":{"id":112538191,"uuid":"123938207","full_name":"simoninithomas/CatDCGAN","owner":"simoninithomas","description":"A DCGAN that generate Cat pictures 🐱‍💻","archived":false,"fork":false,"pushed_at":"2021-04-05T14:34:53.000Z","size":36023,"stargazers_count":203,"open_issues_count":7,"forks_count":68,"subscribers_count":7,"default_branch":"master","last_synced_at":"2025-03-31T21:42:52.555Z","etag":null,"topics":["cats","dcgan","dcgan-tensorflow","deep-learning","gan","tensorflow"],"latest_commit_sha":null,"homepage":"https://simoninithomas.github.io/CatDCGAN/","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/simoninithomas.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}},"created_at":"2018-03-05T15:19:06.000Z","updated_at":"2025-03-22T22:34:43.000Z","dependencies_parsed_at":"2023-05-15T21:15:12.106Z","dependency_job_id":null,"html_url":"https://github.com/simoninithomas/CatDCGAN","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/simoninithomas%2FCatDCGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simoninithomas%2FCatDCGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simoninithomas%2FCatDCGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simoninithomas%2FCatDCGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/simoninithomas","download_url":"https://codeload.github.com/simoninithomas/CatDCGAN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253445938,"owners_count":21909884,"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":["cats","dcgan","dcgan-tensorflow","deep-learning","gan","tensorflow"],"created_at":"2024-11-17T04:15:21.283Z","updated_at":"2025-05-10T16:32:36.258Z","avatar_url":"https://github.com/simoninithomas.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CatDCGAN 🐱‍💻\nA DGAN that generate Cat pictures\n\u003cbr\u003e\n\u003cimg src=\"assets/output.png\" alt=\"CatDCGAN Output\" /\u003e\n\n\u003cp\u003e Cat DCGAN is a Deep Convolutional Generative Adversarial Network (DCGAN) \u003cb\u003ethat generates pictures of cats\u003c/b\u003e \u003c/p\u003e\nThis is an open source project \n\u003cbr\u003e\n\n## The tutorial 📃\nIf you want to implement it by yourself and understand how it works, \u003cb\u003eplease read my article on FreeCodeCamp\u003c/b\u003e  https://medium.freecodecamp.org/how-ai-can-learn-to-generate-pictures-of-cats-ba692cb6eae4\n\n\u003cbr\u003e\n\n## Links 🔗\n🌐 : https://simoninithomas.github.io/CatDCGAN/\n\u003cbr\u003e\u003cbr\u003e\n\u003cp\u003e If you have any questions, \u003cb\u003e feel free to ask me: \u003c/b\u003e \u003c/p\u003e\n\u003cp\u003e 📧: \u003ca href=\"mailto:hello@simoninithomas.com\"\u003ehello@simoninithomas.com\u003c/a\u003e  \u003c/p\u003e\n\u003cp\u003e Github: https://github.com/simoninithomas/CatDCGAN \u003c/p\u003e\n\u003cp\u003e 🌐 : https://www.simoninithomas.com \u003c/p\u003e\n\u003cp\u003e Twitter: \u003ca href=\"https://twitter.com/ThomasSimonini\"\u003e@ThomasSimonini\u003c/a\u003e \u003c/p\u003e\n\nIn this part we're going to implement the DCGAN.\nOur Architecture:\u003cbr\u003e\u003cbr\u003e\n\u003cimg src=\"assets/GDSchema.png\" alt=\"Cat DCGAN Architecture\"/\u003e\n\n## Getting Started 📝\n- Download the dataset here: https://www.kaggle.com/crawford/cat-dataset\n- \u003cb\u003e Download the model checkpoint \u003c/b\u003e : https://drive.google.com/drive/folders/1zdZZ91fjOUiOsIdAQKZkUTATXzqy7hiz?usp=sharing\n- Type `sh start.sh` it will handle extract, remove outliers, normalization and face centering\n- Launch Jupyter Notebook `jupyter notebook --no-browser`\n- Launch CatDCGAN\n- Change `do_preprocess = True` ⚠️⚠️⚠️ important!\n- \u003cb\u003e If you want to train from scratch \u003c/b\u003e: change `from_checkpoint = False`\n- \u003cb\u003e If you want to train from last model saved (you save 20 hours of training 🎉)\u003c/b\u003e : change `from_checkpoint = True`\n\n## Important note 🤔\n\u003cb\u003e You can't run this on your computer \u003c/b\u003e (except if you have GPUs or wait 10 years 😅), personally I train this DCGAN for 20 hours with Microsoft Azure and their Deep Learning Virtual Machine (they offer 170$)\nhttps://azuremarketplace.microsoft.com/en-us/marketplace/apps/microsoft-ads.dsvm-deep-learning\n\u003cbr\u003e\n⚠️ I don't have any business relations with them. I just loved their excellent customer service.\n\nIf you have some troubles to use follow the explainations of this excellent article here (without last the part fast.ai): https://medium.com/@manikantayadunanda/setting-up-deeplearning-machine-and-fast-ai-on-azure-a22eb6bd6429\n\n## Contributing 🙌\nIf you want to contribute to the project, your help is very welcome. This is an open source project.\n\n![](https://media.giphy.com/media/14cAg6Rn5jndIc/giphy.gif)\n\n\nWe currently working on improving our Generative adversarial network architecture. If you're motivated come join us and submit your pull requests.\n\n## Acknowledgements 👏\nThis project was made possible thanks to:\n- Udacity Face Generator Project \n- The start.sh and preprocess part (modified) made by Alexia Jolicoeur-Martineau https://ajolicoeur.wordpress.com/cats/\n- Siraj's Raval PokeGan https://github.com/llSourcell/Pokemon_GAN\n- The choice of learning rate by Alexia Jolicoeur-Martineau https://ajolicoeur.wordpress.com/cats/\n\n\n\u003cbr\u003e\n\u003cbr\u003e\n\u003cimg src=\"assets/training2.gif\" alt=\"Training DCGAN\" /\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsimoninithomas%2Fcatdcgan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsimoninithomas%2Fcatdcgan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsimoninithomas%2Fcatdcgan/lists"}