{"id":19349381,"url":"https://github.com/koldim2001/unet-pytorch-training","last_synced_at":"2025-04-13T02:36:06.170Z","repository":{"id":235904784,"uuid":"791498616","full_name":"Koldim2001/Unet-pytorch-training","owner":"Koldim2001","description":"Репозиторий для обучения нейросетевых моделей по семантической сегментации + пример использования моделей на практике","archived":false,"fork":false,"pushed_at":"2025-01-23T15:15:33.000Z","size":57771,"stargazers_count":28,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-26T20:05:25.300Z","etag":null,"topics":["camvid-dataset","cvat","hair-segmentation","pytorch-segmentation","segmentation","segmentation-training","semantic-segmentation","skin-segmentation","streamlit-webapp","unet","unet-image-segmentation","unet-pytorch"],"latest_commit_sha":null,"homepage":"https://image-editor-unet-pytorch.streamlit.app/","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/Koldim2001.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":"2024-04-24T20:35:36.000Z","updated_at":"2025-03-24T11:07:43.000Z","dependencies_parsed_at":"2024-11-10T04:36:11.941Z","dependency_job_id":null,"html_url":"https://github.com/Koldim2001/Unet-pytorch-training","commit_stats":null,"previous_names":["koldim2001/unet-pytorch-training"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Koldim2001%2FUnet-pytorch-training","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Koldim2001%2FUnet-pytorch-training/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Koldim2001%2FUnet-pytorch-training/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Koldim2001%2FUnet-pytorch-training/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Koldim2001","download_url":"https://codeload.github.com/Koldim2001/Unet-pytorch-training/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248657852,"owners_count":21140843,"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":["camvid-dataset","cvat","hair-segmentation","pytorch-segmentation","segmentation","segmentation-training","semantic-segmentation","skin-segmentation","streamlit-webapp","unet","unet-image-segmentation","unet-pytorch"],"created_at":"2024-11-10T04:26:02.233Z","updated_at":"2025-04-13T02:36:06.137Z","avatar_url":"https://github.com/Koldim2001.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Репозиторий для обучения нейросетевых моделей по семантической сегментации + пример использования моделей на примере веб-приложения \n\nНоутбук для обучения сети Unet - [__baseline-train.ipynb__](https://nbviewer.org/github/Koldim2001/Unet-pytorch-training/blob/main/baseline-train.ipynb) \\\nКод написан под формат данных CamVid из CVAT\n\nКод веб-сервиса по изменению цвета волос и кожи, основанный на работе нейронной сети из примера - __web.py__. В примере рассматривается сеть, которая сегментирует кожу и волосы на фотографиях. \nCсылка на сайт - [веб-приложение](https://image-editor-unet-pytorch.streamlit.app/)\n\n![Пример работы сайта](models/web_example.gif)\n\ncamvid-dataset из видео (трехклассовая сегментация) доступен по этой ссылке - [DATASET](https://drive.google.com/file/d/1Vezw0oGxn8eUMMiH7StNgA1EtYfLev0l/view?usp=sharing)\n\n\n\n## __УСТАНОВКА:__\nНеобходимо иметь установленный python 3 любой версии. \\\nДанные команды требуется запускать последовательно в терминале:\n1. Склонируйте к себе этот репозиторий \n2. Перейдите с помощью команды cd в созданную папку \n3. Загрузите все необходимые библиотеки: \n\nPS: Лучше torch ставить сразу с поддержкой gpu __если она имеется__: \n```\npip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121\n```\nлибо если нет cuda:\n```\npip install torch torchvision\n```\nдалее запустить надо:\n```\npip install -r requirements.txt\n```\n---\n\nПосле этого можно работать с ноубуком обучения.\\\nНо если есть желание запустить локально веб-сайт, то необходимо в терминате запустить эту команду:\n```\nstreamlit run web.py\n```\n\n\n---\n\n## Webinar/Tutorial\nИмеется подробный туториал по работе с данным репозиторием, в котором рассказаны основные теоретические и практические моменты по обучению моделей семантической сегментации + использования моделей на практике\\\nYouTube видео доступно по [__ССЫЛКЕ__](https://www.youtube.com/watch?v=zpyzBR3MuT0)\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkoldim2001%2Funet-pytorch-training","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkoldim2001%2Funet-pytorch-training","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkoldim2001%2Funet-pytorch-training/lists"}