{"id":14958922,"url":"https://github.com/avhirupc/semantic-image-completion","last_synced_at":"2025-10-29T09:52:14.988Z","repository":{"id":100799744,"uuid":"81206517","full_name":"avhirupc/Semantic-Image-Completion","owner":"avhirupc","description":"Implementation of : Semantic Image Inpainting with Perceptual and Contextual Losses Raymond","archived":false,"fork":false,"pushed_at":"2020-03-04T09:43:52.000Z","size":375,"stargazers_count":23,"open_issues_count":2,"forks_count":10,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-10-24T16:37:47.136Z","etag":null,"topics":["computer-vision","deep-learning","deep-neural-networks","image-inpainting","machine-learning","python","tensorflow-experiments"],"latest_commit_sha":null,"homepage":null,"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/avhirupc.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":"2017-02-07T12:39:48.000Z","updated_at":"2023-09-25T13:37:13.000Z","dependencies_parsed_at":"2023-06-10T01:45:28.983Z","dependency_job_id":null,"html_url":"https://github.com/avhirupc/Semantic-Image-Completion","commit_stats":{"total_commits":8,"total_committers":3,"mean_commits":"2.6666666666666665","dds":0.25,"last_synced_commit":"8bd14af8a5e1c1ec14462bd43db78b60d64d30b1"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/avhirupc/Semantic-Image-Completion","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avhirupc%2FSemantic-Image-Completion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avhirupc%2FSemantic-Image-Completion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avhirupc%2FSemantic-Image-Completion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avhirupc%2FSemantic-Image-Completion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/avhirupc","download_url":"https://codeload.github.com/avhirupc/Semantic-Image-Completion/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avhirupc%2FSemantic-Image-Completion/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":281600620,"owners_count":26528905,"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":"2025-10-29T02:00:06.901Z","response_time":59,"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":["computer-vision","deep-learning","deep-neural-networks","image-inpainting","machine-learning","python","tensorflow-experiments"],"created_at":"2024-09-24T13:18:32.209Z","updated_at":"2025-10-29T09:52:14.964Z","avatar_url":"https://github.com/avhirupc.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Semantic Inpainting using DCGANs\n* * *\nThis is an experimental tensorflow implementation of semantic inpainting from corrupted images using DCGANs from the paper [Semantic Image Inpainting with Perceptual and Contextual Losses](https://arxiv.org/abs/1607.07539). A major help was Brandon Amos blog on [Image Completion](https://bamos.github.io/2016/08/09/deep-completion/).One of the major difference between is the training method used.I have used Adam Optimizer instead of gradient descent.\n* * * *\n## Requirements\n* Tensorflow\n* glob\n* Python 3\n\n* * * *\n## Dataset\n* I have used Celebrity faces dataset [CelebA](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html).Download the aligned version ,extract in the same directory as the code\n\n* * * *\n## Model Architecture\n\n![alt-text](images/model.png)\n\n* * *\n## Few Results are Partial Training\n\n\u003eNote: Due to unavailabity of GPU,i didnt train the model for long.This results are after an hour of training\n\n\n![alt-text](images/1.jpg) ![alt-text](images/63.jpg)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Favhirupc%2Fsemantic-image-completion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Favhirupc%2Fsemantic-image-completion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Favhirupc%2Fsemantic-image-completion/lists"}