{"id":16895101,"url":"https://github.com/bloc97/torch-vdsr","last_synced_at":"2026-03-08T00:31:04.414Z","repository":{"id":108163630,"uuid":"80351037","full_name":"bloc97/Torch-VDSR","owner":"bloc97","description":"Torch implementation of the VDSR-CNN Upscaling algorithm","archived":false,"fork":false,"pushed_at":"2017-02-16T19:45:44.000Z","size":2506,"stargazers_count":5,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-06-05T00:51:21.836Z","etag":null,"topics":["cnn","convolutional-neural-networks","neural-network","srcnn","super-resolution","torch","torch-vdsr","torch7","upscaling","vdsr","vdsr-algorithm"],"latest_commit_sha":null,"homepage":null,"language":"Lua","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/bloc97.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"License.txt","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":"2017-01-29T14:36:37.000Z","updated_at":"2021-10-26T20:43:12.000Z","dependencies_parsed_at":null,"dependency_job_id":"4f5b83b1-a337-4548-87ed-58c7b49fab46","html_url":"https://github.com/bloc97/Torch-VDSR","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bloc97/Torch-VDSR","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bloc97%2FTorch-VDSR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bloc97%2FTorch-VDSR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bloc97%2FTorch-VDSR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bloc97%2FTorch-VDSR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bloc97","download_url":"https://codeload.github.com/bloc97/Torch-VDSR/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bloc97%2FTorch-VDSR/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30238836,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-08T00:30:53.000Z","status":"ssl_error","status_checked_at":"2026-03-08T00:30:44.061Z","response_time":53,"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":["cnn","convolutional-neural-networks","neural-network","srcnn","super-resolution","torch","torch-vdsr","torch7","upscaling","vdsr","vdsr-algorithm"],"created_at":"2024-10-13T17:21:15.905Z","updated_at":"2026-03-08T00:31:03.938Z","avatar_url":"https://github.com/bloc97.png","language":"Lua","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Torch-VDSR\nTorch implementation of the VDSR-CNN Upscaling algorithm\n\nThis is a simple torch implementation of the VDSR algorithm from this paper, though some hyperparameters were modified for faster convergence.  \n[Jiwon Kim, Jung Kwon Lee and Kyoung Mu Lee, **Accurate Image Super-Resolution Using Very Deep Convolutional Networks**][1]\n\n\nIncluded model uses only 8 layers (instead of the paper's 20), was trained for 2 hours on a R9 290x using 7 high-resolution images.  \n\nThis is a preliminary test so the results are not the best. When I have time I will train the full 20 layer model using a bigger dataset (around 1000 images).  \n\n![miku comparison](https://github.com/bloc97/Torch-VDSR/raw/master/demo/miku_comp.png)\n![bird comparison](https://github.com/bloc97/Torch-VDSR/raw/master/demo/bird_comp.png ) \n\n[1]: https://arxiv.org/abs/1511.04587\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbloc97%2Ftorch-vdsr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbloc97%2Ftorch-vdsr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbloc97%2Ftorch-vdsr/lists"}