{"id":28631127,"url":"https://github.com/zaccharieramzi/tf-didn","last_synced_at":"2026-04-24T21:31:38.064Z","repository":{"id":81939485,"uuid":"271322840","full_name":"zaccharieramzi/tf-didn","owner":"zaccharieramzi","description":"An unofficial implementation of the Deep iterative down-up CNN for image denoising","archived":false,"fork":false,"pushed_at":"2020-06-12T12:55:16.000Z","size":10,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-12T13:11:29.669Z","etag":null,"topics":["denoising","neural-network","tensorflow"],"latest_commit_sha":null,"homepage":"http://openaccess.thecvf.com/content_CVPRW_2019/html/NTIRE/Yu_Deep_Iterative_Down-Up_CNN_for_Image_Denoising_CVPRW_2019_paper.html","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zaccharieramzi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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,"zenodo":null}},"created_at":"2020-06-10T16:03:32.000Z","updated_at":"2022-07-21T18:25:38.000Z","dependencies_parsed_at":null,"dependency_job_id":"24087cac-44fd-4b43-8acd-0509173d9226","html_url":"https://github.com/zaccharieramzi/tf-didn","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/zaccharieramzi/tf-didn","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaccharieramzi%2Ftf-didn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaccharieramzi%2Ftf-didn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaccharieramzi%2Ftf-didn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaccharieramzi%2Ftf-didn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zaccharieramzi","download_url":"https://codeload.github.com/zaccharieramzi/tf-didn/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaccharieramzi%2Ftf-didn/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32241578,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-24T13:21:15.438Z","status":"ssl_error","status_checked_at":"2026-04-24T13:21:15.005Z","response_time":64,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["denoising","neural-network","tensorflow"],"created_at":"2025-06-12T13:10:15.690Z","updated_at":"2026-04-24T21:31:38.059Z","avatar_url":"https://github.com/zaccharieramzi.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TensorFlow implementation of the Deep iterative down-up CNN\n\n[![Build Status](https://travis-ci.com/zaccharieramzi/tf-didn.svg?branch=master)](https://travis-ci.com/zaccharieramzi/tf-didn)\n\nThe Deep iterative down-up CNN (DIDN) is a network introduced by Songhyun Yu et\nal. in \"Deep Iterative Down-Up CNN for Image Denoising\" CVPR 2019.\nIf you use this network, please cite their work appropriately.\n\nThe official implementation is available [here](https://github.com/SonghyunYu/DIDN)\nin Pytorch.\n\nThe goal of this implementation in TensorFlow is to be easy to read and to adapt:\n- all the code is in one file\n- defaults are those from the paper\n- there is no other imports than from TensorFlow\n\nSome implementation details were taken from the code and not the paper itself:\n- no bias is used in the convolutions\n- the number of down-up blocks is set to 6\n- the activation of the last convolutional layer of the network is linear\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzaccharieramzi%2Ftf-didn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzaccharieramzi%2Ftf-didn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzaccharieramzi%2Ftf-didn/lists"}