{"id":21504004,"url":"https://github.com/znxlwm/tensorflow-pix2pix","last_synced_at":"2025-10-18T00:53:03.496Z","repository":{"id":255470765,"uuid":"100430746","full_name":"znxlwm/tensorflow-pix2pix","owner":"znxlwm","description":"Tensorflow implementation of pix2pix for various datasets.","archived":false,"fork":false,"pushed_at":"2017-08-22T09:19:20.000Z","size":32241,"stargazers_count":6,"open_issues_count":1,"forks_count":3,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-07-16T21:05:10.489Z","etag":null,"topics":["cgan","conditional-gan","gan","generative-adversarial-network","generative-model","image-translation","pix2pix","tensorflow","tensorflow-pix2pix","unet"],"latest_commit_sha":null,"homepage":null,"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/znxlwm.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":"2017-08-16T00:30:49.000Z","updated_at":"2024-04-22T16:12:36.000Z","dependencies_parsed_at":"2024-09-05T15:58:48.372Z","dependency_job_id":null,"html_url":"https://github.com/znxlwm/tensorflow-pix2pix","commit_stats":null,"previous_names":["znxlwm/tensorflow-pix2pix"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/znxlwm/tensorflow-pix2pix","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/znxlwm%2Ftensorflow-pix2pix","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/znxlwm%2Ftensorflow-pix2pix/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/znxlwm%2Ftensorflow-pix2pix/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/znxlwm%2Ftensorflow-pix2pix/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/znxlwm","download_url":"https://codeload.github.com/znxlwm/tensorflow-pix2pix/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/znxlwm%2Ftensorflow-pix2pix/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274776758,"owners_count":25347639,"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","status":"online","status_checked_at":"2025-09-12T02:00:09.324Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["cgan","conditional-gan","gan","generative-adversarial-network","generative-model","image-translation","pix2pix","tensorflow","tensorflow-pix2pix","unet"],"created_at":"2024-11-23T18:48:20.904Z","updated_at":"2025-10-18T00:53:03.397Z","avatar_url":"https://github.com/znxlwm.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# tensorflow-pix2pix\nTensorflow implementation of pix2pix [1] for various datasets.\n\n* you can download datasets: https://people.eecs.berkeley.edu/~tinghuiz/projects/pix2pix/datasets/\n* you can see more information for network architecture and training details in https://arxiv.org/pdf/1611.07004.pdf\n\n## dataset\n* cityscapes\n  * 2,975 training images, 200 train epochs, 1 batch size, inverse order: True\n* facades\n  * 400 training images, 200 train epochs, 1 batch size, inverse order: True\n* maps\n  * 1,096 training images, 200 train epochs, 1 batch size, inverse order: True\n* edges2shoes\n  * 50k training images, 15 train epochs, 4 batch size, inverse order: False\n* edges2handbags\n  * 137k training images, 15 train epochs, 4 batch size, inverse order: False\n\n## Resutls\n### maps\n* facades after 200 epochs\n\u003ctable align='center'\u003e\n\u003ctr align='center'\u003e\n\u003ctd\u003e Input \u003c/td\u003e\n\u003ctd\u003e Output \u003c/td\u003e\n\u003ctd\u003e Ground truth \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cimg src = 'facades_results/test_results/1_input.png'\u003e\n\u003ctd\u003e\u003cimg src = 'facades_results/test_results/1_output.png'\u003e\n\u003ctd\u003e\u003cimg src = 'facades_results/test_results/1_target.png'\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cimg src = 'facades_results/test_results/2_input.png'\u003e\n\u003ctd\u003e\u003cimg src = 'facades_results/test_results/2_output.png'\u003e\n\u003ctd\u003e\u003cimg src = 'facades_results/test_results/2_target.png'\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cimg src = 'facades_results/test_results/3_input.png'\u003e\n\u003ctd\u003e\u003cimg src = 'facades_results/test_results/3_output.png'\u003e\n\u003ctd\u003e\u003cimg src = 'facades_results/test_results/3_target.png'\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n* Generate animation for fixed inputs\n  * First column: input, second column: output, third column: ground truth\n\n![maps_gif](facades_results/facades_generate_animation.gif)\n\n* Learning time\n  * Avg. per epoch: 54.19 sec; Total 200 epochs: 11,339.61 sec\n  \n### maps\n* maps after 200 epochs\n\u003ctable align='center'\u003e\n\u003ctr align='center'\u003e\n\u003ctd\u003e Input \u003c/td\u003e\n\u003ctd\u003e Output \u003c/td\u003e\n\u003ctd\u003e Ground truth \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cimg src = 'maps_results/test_results/1_input.png'\u003e\n\u003ctd\u003e\u003cimg src = 'maps_results/test_results/1_output.png'\u003e\n\u003ctd\u003e\u003cimg src = 'maps_results/test_results/1_target.png'\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cimg src = 'maps_results/test_results/2_input.png'\u003e\n\u003ctd\u003e\u003cimg src = 'maps_results/test_results/2_output.png'\u003e\n\u003ctd\u003e\u003cimg src = 'maps_results/test_results/2_target.png'\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cimg src = 'maps_results/test_results/3_input.png'\u003e\n\u003ctd\u003e\u003cimg src = 'maps_results/test_results/3_output.png'\u003e\n\u003ctd\u003e\u003cimg src = 'maps_results/test_results/3_target.png'\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n* Generate animation for fixed inputs\n  * First column: input, second column: output, third column: ground truth\n\n![maps_gif](maps_results/maps_generate_animation.gif)\n\n* Learning time\n  * Avg. per epoch: 205.08 sec; Total 200 epochs: 41,622.29 sec\n  \n## Development Environment\n\n* Windows 7\n* GTX1080 ti\n* cuda 8.0\n* Python 3.5.3\n* tensorflow-gpu 1.2.1\n* numpy 1.13.1\n* matplotlib 2.0.2\n* imageio 2.2.0\n\n## Reference\n\n[1] Isola, Phillip, et al. \"Image-to-image translation with conditional adversarial networks.\" arXiv preprint arXiv:1611.07004 (2016).\n\n(Full paper: https://arxiv.org/pdf/1611.07004.pdf)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fznxlwm%2Ftensorflow-pix2pix","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fznxlwm%2Ftensorflow-pix2pix","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fznxlwm%2Ftensorflow-pix2pix/lists"}