{"id":20483293,"url":"https://github.com/ribin-baby/u2net_pytorch","last_synced_at":"2026-04-15T19:40:37.022Z","repository":{"id":217794192,"uuid":"744826701","full_name":"Ribin-Baby/U2Net_pytorch","owner":"Ribin-Baby","description":"pytorch implimentation of u2net architecture","archived":false,"fork":false,"pushed_at":"2024-01-18T18:21:46.000Z","size":83897,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-05T16:15:39.801Z","etag":null,"topics":["background-removal","computer-vision","deeplearning","image-matting","python","pytorch","u2net"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"unlicense","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Ribin-Baby.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}},"created_at":"2024-01-18T04:43:11.000Z","updated_at":"2024-01-20T09:11:45.000Z","dependencies_parsed_at":"2024-01-18T09:31:11.869Z","dependency_job_id":null,"html_url":"https://github.com/Ribin-Baby/U2Net_pytorch","commit_stats":null,"previous_names":["ribin-baby/u2net_pytorch"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Ribin-Baby/U2Net_pytorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ribin-Baby%2FU2Net_pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ribin-Baby%2FU2Net_pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ribin-Baby%2FU2Net_pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ribin-Baby%2FU2Net_pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ribin-Baby","download_url":"https://codeload.github.com/Ribin-Baby/U2Net_pytorch/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ribin-Baby%2FU2Net_pytorch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31857619,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-15T15:24:51.572Z","status":"ssl_error","status_checked_at":"2026-04-15T15:24:39.138Z","response_time":63,"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":["background-removal","computer-vision","deeplearning","image-matting","python","pytorch","u2net"],"created_at":"2024-11-15T16:16:52.990Z","updated_at":"2026-04-15T19:40:37.000Z","avatar_url":"https://github.com/Ribin-Baby.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# U2 NET\n\n\u003cdiv  align=\"center\"\u003e\n\u003cimg  src=\"docs/U2NETPR.png\"  style=\"width: 85%\"\u003e\n\u003cbr\u003e\n\u003cfigcaption\u003e\u003ci\u003eFig.1 - U2Net Architecture\u003c/i\u003e\u003c/figcaption\u003e\n\u003c/div\u003e\n\u003cbr\u003e\n\n* **U2-Net** is a two-level nested U-structure architecture. It uses a novel ReSidual U-block (RSU) module to extract multi-scale features without degrading resolution, allowing the network to go deeper and attain high resolution without significantly increasing memory and computation cost.\n* used for for salient object detection, image segmentation, Image Matting, background removal and other image2image modeling tasks.\n\u003cdiv  align=\"center\"\u003e\n\u003cimg  src=\"docs/u2net.rsu-block.svg\"  style=\"width: 80%\"\u003e\n\u003cbr\u003e\n\u003cfigcaption\u003e\u003ci\u003eFig.2 - UNet or RSU Block\u003c/i\u003e\u003c/figcaption\u003e\n\u003c/div\u003e\n\u003cbr\u003e\n\n* U-Net is a U-shaped encoder-decoder architecture with residual connections between each layers. It captures contextual information and intricate detail.\n* These U-Net blocks in U2Net architecture are called ReSidual U-block or RSU.\n\n*  Example: we have trained an Image Matting model on [P3M-10k](https://paperswithcode.com/dataset/p3m-10k) dataset, and the results are given below.\n\u003cdiv  align=\"center\"\u003e\n\u003cimg  src=\"docs/example_u2net_Segment.png\"  style=\"width: 60%\"\u003e\n\u003cbr\u003e\n\u003cfigcaption\u003e\u003ci\u003eFig.3 - Image Matting  with U2-Net example\u003c/i\u003e\u003c/figcaption\u003e\n\u003c/div\u003e\n\u003cbr\u003e\n\n![training progress](docs/training_progress.gif)\n\u003cfigcaption\u003e\u003ci\u003eFig.4 - Image Matting with U2-Net training progress after each steps\u003c/i\u003e\u003c/figcaption\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fribin-baby%2Fu2net_pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fribin-baby%2Fu2net_pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fribin-baby%2Fu2net_pytorch/lists"}