{"id":13482783,"url":"https://github.com/zsdonghao/Unsup-Im2Im","last_synced_at":"2025-03-27T13:32:40.944Z","repository":{"id":72869916,"uuid":"76729432","full_name":"zsdonghao/Unsup-Im2Im","owner":"zsdonghao","description":"Unsupervised Image to Image Translation with Generative Adversarial Networks","archived":false,"fork":false,"pushed_at":"2020-07-19T03:13:26.000Z","size":2217,"stargazers_count":72,"open_issues_count":4,"forks_count":16,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-03-08T22:32:08.223Z","etag":null,"topics":["deep-learning","gan","generative-adversarial-network","image-to-image","tensorflow","tensorlayer"],"latest_commit_sha":null,"homepage":"https://github.com/zsdonghao/tensorlayer","language":"Python","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/zsdonghao.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}},"created_at":"2016-12-17T14:46:12.000Z","updated_at":"2025-02-02T16:37:38.000Z","dependencies_parsed_at":"2023-06-14T13:15:27.251Z","dependency_job_id":null,"html_url":"https://github.com/zsdonghao/Unsup-Im2Im","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zsdonghao%2FUnsup-Im2Im","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zsdonghao%2FUnsup-Im2Im/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zsdonghao%2FUnsup-Im2Im/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zsdonghao%2FUnsup-Im2Im/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zsdonghao","download_url":"https://codeload.github.com/zsdonghao/Unsup-Im2Im/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245854658,"owners_count":20683394,"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":["deep-learning","gan","generative-adversarial-network","image-to-image","tensorflow","tensorlayer"],"created_at":"2024-07-31T17:01:05.468Z","updated_at":"2025-03-27T13:32:40.361Z","avatar_url":"https://github.com/zsdonghao.png","language":"Python","funding_links":[],"categories":["Models/Projects"],"sub_categories":[],"readme":"## Unsupervised Image to Image Translation with Generative Adversarial Networks\n\n\u003ca href=\"http://tensorlayer.readthedocs.io\"\u003e\n\u003cdiv align=\"center\"\u003e\n\t\u003cimg src=\"img/results.png\" width=\"70%\" height=\"70%\"/\u003e\n\u003c/div\u003e\n\u003c/a\u003e\n\n##### Paper: [Unsupervised Image to Image Translation with Generative Adversarial Networks](https://arxiv.org/abs/1701.02676)\n\n### Requirements\n* TensorFlow 1.0.0\n* TensorLayer 1.3.11\n* CUDA 8\n* Ubuntu \n\n### Dataset\n* Before training the network, please prepare the data\n* CelebA [download](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html)\n* Cropped SVHN [download](http://ufldl.stanford.edu/housenumbers/)\n* MNIST [download](https://github.com/myleott/mnist_png/blob/master/mnist_png.tar.gz), and put to `data/mnist_png`\n\n### Usage\n\n#### Step 1: Learning shared feature\n```\npython3 train.py --train_step=\"ac_gan\" --retrain=1\n```\n#### Step 2: Learning image encoder\n```\npython3 train.py --train_step=\"imageEncoder\" --retrain=1\n```\n#### Step 3: Translation\n```\npython3 translate_image.py\n```\n* Samples of all steps will be saved to data/samples/\n\n### Network\n\u003ca href=\"http://tensorlayer.readthedocs.io\"\u003e\n\u003cdiv align=\"center\"\u003e\n\t\u003cimg src=\"img/network.png\" width=\"70%\" height=\"70%\"/\u003e\n\u003c/div\u003e\n\u003c/a\u003e\n\n#### Want to use different datasets?\n* in `train.py` and `translate_image.py` modify the name of dataset `flags.DEFINE_string(\"dataset\", \"celebA\", \"The name of dataset [celebA, obama_hillary]\")`\n* write your own `data_loader` in `data_loader.py`\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzsdonghao%2FUnsup-Im2Im","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzsdonghao%2FUnsup-Im2Im","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzsdonghao%2FUnsup-Im2Im/lists"}