{"id":20932247,"url":"https://github.com/netherquartz/peoplebehinddetector","last_synced_at":"2026-04-24T11:04:39.772Z","repository":{"id":94922113,"uuid":"379659958","full_name":"NetherQuartz/PeopleBehindDetector","owner":"NetherQuartz","description":"Итоговый проект первого семестра Deep Learning School","archived":false,"fork":false,"pushed_at":"2021-06-28T20:59:44.000Z","size":7904,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-19T19:16:24.912Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/NetherQuartz.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}},"created_at":"2021-06-23T16:05:58.000Z","updated_at":"2021-06-28T20:59:47.000Z","dependencies_parsed_at":"2023-07-30T03:16:09.158Z","dependency_job_id":null,"html_url":"https://github.com/NetherQuartz/PeopleBehindDetector","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NetherQuartz%2FPeopleBehindDetector","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NetherQuartz%2FPeopleBehindDetector/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NetherQuartz%2FPeopleBehindDetector/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NetherQuartz%2FPeopleBehindDetector/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NetherQuartz","download_url":"https://codeload.github.com/NetherQuartz/PeopleBehindDetector/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243324504,"owners_count":20273113,"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":[],"created_at":"2024-11-18T21:47:38.151Z","updated_at":"2025-12-28T11:57:42.915Z","avatar_url":"https://github.com/NetherQuartz.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PeopleBehindDetector\n[![Pylint](https://github.com/NetherQuartz/PeopleBehindDetector/actions/workflows/pylint.yml/badge.svg)](https://github.com/NetherQuartz/PeopleBehindDetector/actions/workflows/pylint.yml)\n\nИтоговый проект первого семестра Deep Learning School — веб-приложение для обнаружения людей, стоящих позади пользователя.\n\n## :bookmark_tabs: План выполнения\nЯ выбрал первый сценарий работы, так что мой план выглядит следующим образом:\n\n- [X] Выбор фреймворка/библиотеки для использования детектора \n- [X] Запуск детектора на случайных изображениях\n- [X] Выбор фреймворка/библиотеки для разработки веб/мобильного демо\n- [X] Разработка демо\n- [X] Встраивание модели-детектора в демо\n- [X] Тестирование демо\n- [X] Оформления демо для показа другим людям\n\n## Небольшой отчёт\nМодель — `ssdlite320_mobilenet_v3_large` из `torchvision`, она мало весит и достаточно быстро работает. Само веб-приложение написано с использованием библиотеки `streamlit`.\n\nВ приложении есть возможность как протестировать модель на любых изображениях, загружая их с диска, так и запустить детекцию людей на видео с вебкамеры. Люди обводятся красными прямоугольниками с подписью степени уверенности модели. Пороговая уверенность задаётся слайдером.\n\n## Демо\nДемо доступно на [Heroku](https://people-behind-detector.herokuapp.com/) и [Streamlit Sharing](https://share.streamlit.io/netherquartz/peoplebehinddetector/main/main.py). Прошу иметь в виду, что из-за сильной задержки вебкамера может не работать или работать не так, как ожидается. В этом случае рекомендую запустить приложение локально.\n\n## Локальный запуск\n1. Установите Python 3.8\n2. Склонируйте проект: `git clone https://github.com/NetherQuartz/PeopleBehindDetector.git`\n### Вариант 1. Poetry\n```Bash\n$ pip3 install poetry\n$ poetry install\n$ ./run.sh\n```\n\n### Вариант 2. requirements.txt\n```Bash\n$ pip install -r requirements.txt\n$ streamlit run main.py\n```\n![demo](demo.gif)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnetherquartz%2Fpeoplebehinddetector","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnetherquartz%2Fpeoplebehinddetector","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnetherquartz%2Fpeoplebehinddetector/lists"}