{"id":13719372,"url":"https://github.com/thevarunsharma/Image-Colorization","last_synced_at":"2025-05-07T11:31:31.368Z","repository":{"id":111637403,"uuid":"164070375","full_name":"thevarunsharma/Image-Colorization","owner":"thevarunsharma","description":"Automatic Image Colorization using a Convolutional Network (U-Net)","archived":false,"fork":false,"pushed_at":"2020-04-29T07:46:22.000Z","size":425,"stargazers_count":11,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-11-14T08:36:21.752Z","etag":null,"topics":["convolutional-neural-networks","deep-learning","flask-application","image-colorization","keras","machine-learning","python","tensorflow"],"latest_commit_sha":null,"homepage":"","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/thevarunsharma.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":"2019-01-04T06:56:18.000Z","updated_at":"2024-04-10T05:07:45.000Z","dependencies_parsed_at":"2023-05-24T18:30:12.885Z","dependency_job_id":null,"html_url":"https://github.com/thevarunsharma/Image-Colorization","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/thevarunsharma%2FImage-Colorization","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thevarunsharma%2FImage-Colorization/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thevarunsharma%2FImage-Colorization/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thevarunsharma%2FImage-Colorization/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/thevarunsharma","download_url":"https://codeload.github.com/thevarunsharma/Image-Colorization/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252868850,"owners_count":21816925,"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":["convolutional-neural-networks","deep-learning","flask-application","image-colorization","keras","machine-learning","python","tensorflow"],"created_at":"2024-08-03T01:00:47.308Z","updated_at":"2025-05-07T11:31:30.513Z","avatar_url":"https://github.com/thevarunsharma.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003ch1\u003eImage-Colorization\u003c/h1\u003e\n\u003ch2\u003eAutomatic Image Colorization using a Convolutional Network (U-Net)\u003c/h2\u003e\n\u003cul\u003e\n  \u003cli\u003eUsing the U-Net ConvNet Architecture for end-to-end image colorization.\u003c/li\u003e\n  \u003cli\u003eTakes as input a grayscale 32x32 image and returns a colorized 32x32 version\u003c/li\u003e\n  \u003cli\u003eThe model has been trained on the CIFAR-10 32x32 images for 100 epochs.\u003c/li\u003e\n  \u003cli\u003eThe model achieved an accuracy of \u003cstrong\u003e55.14%\u003c/strong\u003e and a mean absolute error(MAE) of \u003cstrong\u003e0.0464\u003c/strong\u003e on the test set.\u003c/li\u003e \n \u003c/ul\u003e\n\u003cbr/\u003e\n\u003ch2\u003eModel Achitecture\u003c/h2\u003e\n\u003cp\u003eThe model uses U-Net architecture which uses skip connections to preserve the lower level details and structute of an image, that are lost due to contracting bottle-neck.\u003c/p\u003e\n\u003cp align='center'\u003e\n  \u003cimg src='UNet.png' width='800vw'\u003e\u003cbr/\u003e\u003cem\u003eThe U-Net Architecture\u003c/em\u003e\n\u003c/p\u003e\n\u003cbr/\u003e\n\u003ch2\u003eDemo\u003c/h2\u003e\n\u003cp\u003eA web interface has been implemented, where a user uploads a grayscale image as input and gets a colored image displayed as output\u003c/p\u003e\n\u003cp align='center'\u003e\n  \u003ckbd\u003e\u003cimg src='demo.png' width='800vw'\u003e\u003c/kbd\u003e\u003cbr/\u003e\u003cem\u003eSample Run\u003c/em\u003e\n\u003c/p\u003e\n\u003cbr/\u003e\n\u003ch2\u003eRequirements\u003c/h2\u003e\n\u003cul\u003e\n  \u003cli\u003eNumPy\u003c/li\u003e\n  \u003cli\u003eTensorflow\u003c/li\u003e\n  \u003cli\u003eKeras\u003c/li\u003e\n  \u003cli\u003eSciPy\u003c/li\u003e\n  \u003cli\u003eFlask\u003c/li\u003e\n\u003c/ul\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthevarunsharma%2FImage-Colorization","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthevarunsharma%2FImage-Colorization","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthevarunsharma%2FImage-Colorization/lists"}