{"id":13936342,"url":"https://github.com/ternaus/TernausNet","last_synced_at":"2025-07-19T21:32:25.833Z","repository":{"id":44438458,"uuid":"115770399","full_name":"ternaus/TernausNet","owner":"ternaus","description":"UNet model with VGG11 encoder pre-trained on Kaggle Carvana dataset","archived":false,"fork":false,"pushed_at":"2022-10-26T02:20:58.000Z","size":85884,"stargazers_count":1058,"open_issues_count":10,"forks_count":246,"subscribers_count":30,"default_branch":"master","last_synced_at":"2025-06-24T19:46:30.281Z","etag":null,"topics":["image-segmentation","pytorch"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1801.05746","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/ternaus.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null},"funding":{"github":null,"patreon":"ternaus","open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"custom":null}},"created_at":"2017-12-30T03:13:50.000Z","updated_at":"2025-06-05T02:29:36.000Z","dependencies_parsed_at":"2022-07-24T23:46:33.723Z","dependency_job_id":null,"html_url":"https://github.com/ternaus/TernausNet","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/ternaus/TernausNet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ternaus%2FTernausNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ternaus%2FTernausNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ternaus%2FTernausNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ternaus%2FTernausNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ternaus","download_url":"https://codeload.github.com/ternaus/TernausNet/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ternaus%2FTernausNet/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266019657,"owners_count":23864916,"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":["image-segmentation","pytorch"],"created_at":"2024-08-07T23:02:34.857Z","updated_at":"2025-07-19T21:32:20.822Z","avatar_url":"https://github.com/ternaus.png","language":"Python","funding_links":["https://patreon.com/ternaus"],"categories":["Python","Interesting Non EO parts Python"],"sub_categories":["GEDI"],"readme":"# TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation\n\nBy [Vladimir Iglovikov](https://www.linkedin.com/in/iglovikov/) and [Alexey Shvets](https://www.linkedin.com/in/shvetsiya/)\n\n# Introduction\n\nTernausNet is a modification of the celebrated UNet architecture that is widely used for binary Image Segmentation. For more details, please refer to our [arXiv paper](https://arxiv.org/abs/1801.05746).\n\n![UNet11](https://habrastorage.org/webt/hu/ji/ir/hujiirvpgpf7eswq88h_x7ahliw.png)\n\n\n![loss_curve](https://habrastorage.org/webt/no/up/xq/noupxqqk_ivqwv3e7btyxtemt0m.png)\n\nPre-trained encoder speeds up convergence even on the datasets with a different semantic features. Above curve shows validation Jaccard Index (IOU) as a function of epochs for [Aerial Imagery](https://project.inria.fr/aerialimagelabeling/)\n\nThis architecture was a part of the [winning solutiuon](http://blog.kaggle.com/2017/12/22/carvana-image-masking-first-place-interview/) (1st out of 735 teams) in the [Carvana Image Masking Challenge](https://www.kaggle.com/c/carvana-image-masking-challenge).\n\n# Installation\n\n```bash\npip install ternausnet\n```\n\n# Citing TernausNet\nPlease cite TernausNet in your publications if it helps your research:\n\n```\n@ARTICLE{arXiv:1801.05746,\n         author = {V. Iglovikov and A. Shvets},\n          title = {TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation},\n        journal = {ArXiv e-prints},\n         eprint = {1801.05746},\n           year = 2018\n        }\n```\n\n# Example of the train and test pipeline\n\nhttps://github.com/ternaus/robot-surgery-segmentation\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fternaus%2FTernausNet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fternaus%2FTernausNet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fternaus%2FTernausNet/lists"}