[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-chandrikadeb7--Face-Mask-Detection":3,"tool-chandrikadeb7--Face-Mask-Detection":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",140436,2,"2026-04-05T23:32:43",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":80,"owner_email":81,"owner_twitter":75,"owner_website":82,"owner_url":83,"languages":84,"stars":96,"forks":97,"last_commit_at":98,"license":99,"difficulty_score":10,"env_os":100,"env_gpu":101,"env_ram":100,"env_deps":102,"category_tags":111,"github_topics":112,"view_count":10,"oss_zip_url":131,"oss_zip_packed_at":131,"status":16,"created_at":132,"updated_at":133,"faqs":134,"releases":165},640,"chandrikadeb7\u002FFace-Mask-Detection","Face-Mask-Detection","Face Mask Detection system based on computer vision and deep learning using OpenCV and Tensorflow\u002FKeras","Face-Mask-Detection 是一款基于计算机视觉与深度学习技术的开源项目，旨在通过摄像头画面自动判断人员是否佩戴了口罩。它能够同时处理静态图片与实时视频流，实现高效的人脸口罩检测。\n\n面对公共卫生挑战，该项目解决了公共交通、密集区域及企业中缺乏高效防疫监控工具的痛点。其核心优势在于采用了 MobileNetV2 网络架构，在保证检测精度的前提下大幅降低了计算资源消耗，使得模型能够轻松部署在树莓派、Google Coral 等嵌入式硬件上，非常适合边缘计算场景。\n\n这款作品主要面向开发者、人工智能研究人员以及需要进行安防系统集成的工程师。它不仅提供了完整的代码框架，还展示了如何将 TensorFlow 与 OpenCV 结合应用于实际项目。如果你正在寻找一个轻量级且准确的口罩检测方案，或者想学习如何将深度学习模型落地，Face-Mask-Detection 都是一个值得参考的优秀选择。","\u003Ch1 align=\"center\">Face Mask Detection\u003C\u002Fh1>\n\n\u003Cdiv align= \"center\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_ed9c678565c7.png\" width=\"200\" height=\"200\"\u002F>\n  \u003Ch4>Face Mask Detection System built with OpenCV, Keras\u002FTensorFlow using Deep Learning and Computer Vision concepts in order to detect face masks in static images as well as in real-time video streams.\u003C\u002Fh4>\n\u003C\u002Fdiv>\n\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\n![Python](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-v3.6+-blue.svg)\n[![contributions welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcontributions-welcome-brightgreen.svg?style=flat)](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fissues)\n[![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchandrikadeb7\u002FFace-Mask-Detection.svg?logo=github)](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fnetwork\u002Fmembers)\n[![Stargazers](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchandrikadeb7\u002FFace-Mask-Detection.svg?logo=github)](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fstargazers)\n[![Issues](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Fchandrikadeb7\u002FFace-Mask-Detection.svg?logo=github)](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fissues)\n[![LinkedIn](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-LinkedIn-black.svg?style=flat-square&logo=linkedin&colorB=555)](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fchandrika-deb\u002F)\n\n\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\n![Live Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_92dfc6f0dcc1.gif)\n\n## :point_down: Support me here!\n\u003Ca href=\"https:\u002F\u002Fwww.buymeacoffee.com\u002Fchandrikadeb7\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fwww.buymeacoffee.com\u002Fassets\u002Fimg\u002Fcustom_images\u002Forange_img.png\" alt=\"Buy Me A Coffee\" style=\"height: 41px !important;width: 174px !important;box-shadow: 0px 3px 2px 0px rgba(190, 190, 190, 0.5) !important;-webkit-box-shadow: 0px 3px 2px 0px rgba(190, 190, 190, 0.5) !important;\" >\u003C\u002Fa>\n\n## :innocent: Motivation\nAmid the ongoing COVID-19 pandemic, there are no efficient face mask detection applications which are now in high demand for transportation means, densely populated areas, residential districts, large-scale manufacturers and other enterprises to ensure safety. The absence of large datasets of __‘with_mask’__ images has made this task cumbersome and challenging. \n\n## PPT and Project Report sharing costs ₹1000 ($15)\nIf interested, contact me at chandrikadeb7@gmail.com\n\n# 🌟 [Purchase on Gumroad](https:\u002F\u002Fgum.co\u002FGetFaceMask)\n \n## :hourglass: Project Demo\n:movie_camera: [YouTube Demo Link](https:\u002F\u002Fyoutu.be\u002FwYwW7gAYyxw)\n\n:computer: [Dev Link](https:\u002F\u002Fdev.to\u002Fchandrikadeb7\u002Fface-mask-detection-my-major-project-3fj3)\n\n[![Already deployed version](https:\u002F\u002Fraw.githubusercontent.com\u002Fvasantvohra\u002FTrashNet\u002Fmaster\u002Fhr.svg)](https:\u002F\u002Fface-mask--detection-app.herokuapp.com\u002F)\n\n\n\n\u003Cp align=\"center\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_41a440011391.png\" width=\"700\" height=\"400\">\u003C\u002Fp>\n\n\n## :warning: TechStack\u002Fframework used\n\n- [OpenCV](https:\u002F\u002Fopencv.org\u002F)\n- [Caffe-based face detector](https:\u002F\u002Fcaffe.berkeleyvision.org\u002F)\n- [Keras](https:\u002F\u002Fkeras.io\u002F)\n- [TensorFlow](https:\u002F\u002Fwww.tensorflow.org\u002F)\n- [MobileNetV2](https:\u002F\u002Farxiv.org\u002Fabs\u002F1801.04381)\n\n## :star: Features\nOur face mask detector doesn't use any morphed masked images dataset and the model is accurate. Owing to the use of MobileNetV2 architecture, it is computationally efficient, thus making it easier to deploy the model to embedded systems (Raspberry Pi, Google Coral, etc.).\n\nThis system can therefore be used in real-time applications which require face-mask detection for safety purposes due to the outbreak of Covid-19. This project can be integrated with embedded systems for application in airports, railway stations, offices, schools, and public places to ensure that public safety guidelines are followed.\n\n## :file_folder: Dataset\nThe dataset used can be downloaded here - [Click to Download](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Ftree\u002Fmaster\u002Fdataset)\n\nThis dataset consists of __4095 images__ belonging to two classes:\n*\t__with_mask: 2165 images__\n*\t__without_mask: 1930 images__\n\nThe images used were real images of faces wearing masks. The images were collected from the following sources:\n\n* __Bing Search API__ ([See Python script](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fblob\u002Fmaster\u002Fsearch.py))\n* __Kaggle datasets__ \n* __RMFD dataset__ ([See here](https:\u002F\u002Fgithub.com\u002FX-zhangyang\u002FReal-World-Masked-Face-Dataset))\n\n## :key: Prerequisites\n\nAll the dependencies and required libraries are included in the file \u003Ccode>requirements.txt\u003C\u002Fcode> [See here](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fblob\u002Fmaster\u002Frequirements.txt)\n\n## 🚀&nbsp; Installation\n1. Clone the repo\n```\n$ git clone https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection.git\n```\n\n2. Change your directory to the cloned repo \n```\n$ cd Face-Mask-Detection\n```\n\n3. Create a Python virtual environment named 'test' and activate it\n```\n$ virtualenv test\n```\n```\n$ source test\u002Fbin\u002Factivate\n```\n\n4. Now, run the following command in your Terminal\u002FCommand Prompt to install the libraries required\n```\n$ pip3 install -r requirements.txt\n```\n\n## :bulb: Working\n\n1. Open terminal. Go into the cloned project directory and type the following command:\n```\n$ python3 train_mask_detector.py --dataset dataset\n```\n\n2. To detect face masks in an image type the following command: \n```\n$ python3 detect_mask_image.py --image images\u002Fpic1.jpeg\n```\n\n3. To detect face masks in real-time video streams type the following command:\n```\n$ python3 detect_mask_video.py \n```\n## :key: Results\n\n#### Our model gave 98% accuracy for Face Mask Detection after training via \u003Ccode>tensorflow-gpu==2.5.0\u003C\u002Fcode>\n\n\u003Ca href=\"https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1AZ0W2QAHnM3rcj0qbTmc7c3fAMPCowQ1?usp=sharing\">\u003Cimg src=\"https:\u002F\u002Fcolab.research.google.com\u002Fassets\u002Fcolab-badge.svg\" alt=\"Open In Colab\"\u002F>\u003C\u002Fa>\n####          \n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_d3f9c5d1ba32.png)\n\n#### We got the following accuracy\u002Floss training curve plot\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_b35b14c17e48.png)\n\n## Streamlit app\n\nFace Mask Detector webapp using Tensorflow & Streamlit\n\ncommand\n```\n$ streamlit run app.py \n```\n## Images\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_dc91609216e9.png\">\n\u003C\u002Fp>\n\u003Cp align=\"center\">Upload Images\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_89e5baeb6359.png\">\n\u003C\u002Fp>\n\u003Cp align=\"center\">Results\u003C\u002Fp>\n\n## :clap: And it's done!\nFeel free to mail me for any doubts\u002Fquery \n:email: chandrikadeb7@gmail.com\n\n---\n\n## Internet of Things Device Setup\n\n### Expected Hardware\n* [Raspberry Pi 4 4GB with a case](https:\u002F\u002Fwww.canakit.com\u002Fraspberry-pi-4-4gb.html)\n* [5MP OV5647 PiCamera from Arducam](https:\u002F\u002Fwww.arducam.com\u002Fdocs\u002Fcameras-for-raspberry-pi\u002Fnative-raspberry-pi-cameras\u002F5mp-ov5647-cameras\u002F)\n\n### Getting Started\n* Setup the Raspberry Pi case and Operating System by following the Getting Started section on page 3 at `documentation\u002FCanaKit-Raspberry-Pi-Quick-Start-Guide-4.0.pdf` or https:\u002F\u002Fwww.canakit.com\u002FMedia\u002FCanaKit-Raspberry-Pi-Quick-Start-Guide-4.0.pdf\n  * With NOOBS, use the recommended operating system\n* Setup the PiCamera\n  * Assemble the PiCamera case from Arducam using `documentation\u002FArducam-Case-Setup.pdf` or https:\u002F\u002Fwww.arducam.com\u002Fdocs\u002Fcameras-for-raspberry-pi\u002Fnative-raspberry-pi-cameras\u002F5mp-ov5647-cameras\u002F\n  * [Attach your PiCamera module to the Raspberry Pi and enable the camera](https:\u002F\u002Fprojects.raspberrypi.org\u002Fen\u002Fprojects\u002Fgetting-started-with-picamera\u002F2)\n\n### Raspberry Pi App Installation & Execution\n\n> Run these commands after cloning the project\n\n| Commands                                                                                                                     | Time to completion |\n|------------------------------------------------------------------------------------------------------------------------------|--------------------|\n| sudo apt install -y libatlas-base-dev liblapacke-dev gfortran                                                                | 1min               |\n| sudo apt install -y libhdf5-dev libhdf5-103                                                                                  | 1min               |\n| pip3 install -r requirements.txt                                                                                             | 1-3 mins           |\n| wget \"https:\u002F\u002Fraw.githubusercontent.com\u002FPINTO0309\u002FTensorflow-bin\u002Fmaster\u002Ftensorflow-2.4.0-cp37-none-linux_armv7l_download.sh\" | less than 10 secs  |\n| .\u002Ftensorflow-2.4.0-cp37-none-linux_armv7l_download.sh                                                                        | less than 10 secs  |\n| pip3 install tensorflow-2.4.0-cp37-none-linux_armv7l.whl                                                                     | 1-3 mins           |\n\n---\n\n## :trophy: Awards\nAwarded Runners Up position in [Amdocs Innovation India ICE Project Fair]( https:\u002F\u002Fwww.amdocs.com\u002F)\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_0cad02888e08.jpeg)\n\n## :raising_hand: Cited by:\n\n1. https:\u002F\u002Fosf.io\u002Fpreprints\u002F3gph4\u002F\n2. https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-981-33-4673-4_49\n3. https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9312083\u002F\n4. https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-981-33-4673-4_48\n5. https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FAkhyar_Ahmed\u002Fpublication\u002F344173985_Face_Mask_Detector\u002Flinks\u002F5f58c00ea6fdcc9879d8e6f7\u002FFace-Mask-Detector.pdf\n\n## 👏 Appreciation\n\n### Selected in [Devscript Winter Of Code](https:\u002F\u002Fdevscript.tech\u002Fwoc\u002F)\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_fce0ea79a152.jpeg\" height=300 width=300>\n\n### Selected in [Script Winter Of Code](https:\u002F\u002Fswoc.tech\u002Fproject.html)\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_a18b127a4462.jpeg\" height=300 width=300>\n\n### Seleted in [Student Code-in](https:\u002F\u002Fscodein.tech\u002F)\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_9a714af583ac.jpeg\" height=300 width=300>\n\n## :+1: Credits\n* [https:\u002F\u002Fwww.pyimagesearch.com\u002F](https:\u002F\u002Fwww.pyimagesearch.com\u002F)\n* [https:\u002F\u002Fwww.tensorflow.org\u002Ftutorials\u002Fimages\u002Ftransfer_learning](https:\u002F\u002Fwww.tensorflow.org\u002Ftutorials\u002Fimages\u002Ftransfer_learning)\n\n## :handshake: Contribution\n\n#### Please read the Contribution Guidelines [here](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fblob\u002Fmaster\u002FCONTRIBUTING.md)\nFeel free to **file a new issue** with a respective title and description on the the [Face-Mask-Detection](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fissues) repository. If you already found a solution to your problem, **I would love to review your pull request**! \n\n## :handshake: Our Contributors\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_59a96664b1e4.png\" \u002F>\n\u003C\u002Fa>\n\n\n## :eyes: Code of Conduct\n\nYou can find our Code of Conduct [here](\u002FCODE_OF_CONDUCT.md).\n\n## :heart: Owner\nMade with :heart:&nbsp;  by [Chandrika Deb](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7)\n\n## :eyes: License\nMIT © [Chandrika Deb](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fblob\u002Fmaster\u002FLICENSE)\n\n","\u003Ch1 align=\"center\">口罩检测\u003C\u002Fh1>\n\n\u003Cdiv align= \"center\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_ed9c678565c7.png\" width=\"200\" height=\"200\"\u002F>\n  \u003Ch4>基于 OpenCV、Keras\u002FTensorFlow 构建的口罩检测系统，利用深度学习 (Deep Learning) 和计算机视觉 (Computer Vision) 概念，旨在检测静态图像及实时视频流中的口罩。\u003C\u002Fh4>\n\u003C\u002Fdiv>\n\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\n![Python](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-v3.6+-blue.svg)\n[![contributions welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcontributions-welcome-brightgreen.svg?style=flat)](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fissues)\n[![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchandrikadeb7\u002FFace-Mask-Detection.svg?logo=github)](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fnetwork\u002Fmembers)\n[![Stargazers](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchandrikadeb7\u002FFace-Mask-Detection.svg?logo=github)](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fstargazers)\n[![Issues](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Fchandrikadeb7\u002FFace-Mask-Detection.svg?logo=github)](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fissues)\n[![LinkedIn](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-LinkedIn-black.svg?style=flat-square&logo=linkedin&colorB=555)](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fchandrika-deb\u002F)\n\n\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\n![Live Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_92dfc6f0dcc1.gif)\n\n## :point_down: 在此支持我！\n\u003Ca href=\"https:\u002F\u002Fwww.buymeacoffee.com\u002Fchandrikadeb7\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fwww.buymeacoffee.com\u002Fassets\u002Fimg\u002Fcustom_images\u002Forange_img.png\" alt=\"Buy Me A Coffee\" style=\"height: 41px !important;width: 174px !important;box-shadow: 0px 3px 2px 0px rgba(190, 190, 190, 0.5) !important;-webkit-box-shadow: 0px 3px 2px 0px rgba(190, 190, 190, 0.5) !important;\" >\u003C\u002Fa>\n\n## :innocent: 动机\n在持续的 COVID-19 疫情期间，缺乏高效的口罩检测应用程序，而这类应用在交通工具、人口密集区、住宅区、大型制造商及其他企业中需求高涨，以确保安全。由于缺少 __‘佩戴口罩’__ 的大规模图像数据集，使得这项任务变得繁琐且具有挑战性。\n\n## PPT 和项目报告分享费用为 ₹1000 ($15)\n如有兴趣，请通过 chandrikadeb7@gmail.com 联系我\n\n# 🌟 [在 Gumroad 上购买](https:\u002F\u002Fgum.co\u002FGetFaceMask)\n \n## :hourglass: 项目演示\n:movie_camera: [YouTube 演示链接](https:\u002F\u002Fyoutu.be\u002FwYwW7gAYyxw)\n\n:computer: [开发博客链接](https:\u002F\u002Fdev.to\u002Fchandrikadeb7\u002Fface-mask-detection-my-major-project-3fj3)\n\n[![已部署版本](https:\u002F\u002Fraw.githubusercontent.com\u002Fvasantvohra\u002FTrashNet\u002Fmaster\u002Fhr.svg)](https:\u002F\u002Fface-mask--detection-app.herokuapp.com\u002F)\n\n\n\n\u003Cp align=\"center\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_41a440011391.png\" width=\"700\" height=\"400\">\u003C\u002Fp>\n\n\n## :warning: 使用的技术栈\u002F框架\n\n- [OpenCV](https:\u002F\u002Fopencv.org\u002F)\n- [基于 Caffe 的人脸检测器](https:\u002F\u002Fcaffe.berkeleyvision.org\u002F)\n- [Keras](https:\u002F\u002Fkeras.io\u002F)\n- [TensorFlow](https:\u002F\u002Fwww.tensorflow.org\u002F)\n- [MobileNetV2](https:\u002F\u002Farxiv.org\u002Fabs\u002F1801.04381)\n\n## :star: 功能特性\n我们的口罩检测器不使用任何经过变形处理的口罩图像数据集，模型准确度高。得益于 MobileNetV2 架构的使用，它具有计算效率高的特点，从而更容易将模型部署到嵌入式系统（如 Raspberry Pi、Google Coral 等）。\n\n因此，该系统可用于需要出于 Covid-19 爆发原因进行面部口罩检测的实时应用中。该项目可集成到嵌入式系统中，应用于机场、火车站、办公室、学校和公共场所，以确保遵守公共安全指南。\n\n## :file_folder: 数据集\n所使用的数据集可在此下载 - [点击下载](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Ftree\u002Fmaster\u002Fdataset)\n\n该数据集包含 __4095 张图像__，分为两类：\n*\t__佩戴口罩：2165 张图像__\n*\t__未佩戴口罩：1930 张图像__\n\n所使用的图像均为佩戴真实口罩的面部图像。图像收集自以下来源：\n\n* __Bing 搜索 API__ ([查看 Python 脚本](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fblob\u002Fmaster\u002Fsearch.py))\n* __Kaggle 数据集__ \n* __RMFD 数据集__ ([点击查看](https:\u002F\u002Fgithub.com\u002FX-zhangyang\u002FReal-World-Masked-Face-Dataset))\n\n## :key: 前置条件\n\n所有依赖项和所需库均包含在文件 \u003Ccode>requirements.txt\u003C\u002Fcode> 中 [点击查看](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fblob\u002Fmaster\u002Frequirements.txt)\n\n## 🚀&nbsp; 安装\n1. 克隆仓库\n```\n$ git clone https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection.git\n```\n\n2. 更改目录至克隆的仓库\n```\n$ cd Face-Mask-Detection\n```\n\n3. 创建一个名为 'test' 的 Python 虚拟环境并激活它\n```\n$ virtualenv test\n```\n```\n$ source test\u002Fbin\u002Factivate\n```\n\n4. 现在，在您的终端\u002F命令提示符中运行以下命令以安装所需的库\n```\n$ pip3 install -r requirements.txt\n```\n\n## :bulb: 工作原理\n\n1. 打开终端。进入克隆的项目目录并输入以下命令：\n```\n$ python3 train_mask_detector.py --dataset dataset\n```\n\n2. 要在图像中检测口罩，请输入以下命令：\n```\n$ python3 detect_mask_image.py --image images\u002Fpic1.jpeg\n```\n\n3. 要在实时视频流中检测口罩，请输入以下命令：\n```\n$ python3 detect_mask_video.py \n```\n## :key: 结果\n\n#### 我们的模型在使用 \u003Ccode>tensorflow-gpu==2.5.0\u003C\u002Fcode> 训练后，口罩检测准确率达到 98%\n\n\u003Ca href=\"https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1AZ0W2QAHnM3rcj0qbTmc7c3fAMPCowQ1?usp=sharing\">\u003Cimg src=\"https:\u002F\u002Fcolab.research.google.com\u002Fassets\u002Fcolab-badge.svg\" alt=\"Open In Colab\"\u002F>\u003C\u002Fa>\n####          \n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_d3f9c5d1ba32.png)\n\n#### 我们得到了以下准确率\u002F损失训练曲线图\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_b35b14c17e48.png)\n\n## Streamlit 应用\n\n使用 Tensorflow 和 Streamlit 构建的口罩检测 Web 应用\n\n命令\n```\n$ streamlit run app.py \n```\n## 图片\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_dc91609216e9.png\">\n\u003C\u002Fp>\n\u003Cp align=\"center\">上传图片\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_89e5baeb6359.png\">\n\u003C\u002Fp>\n\u003Cp align=\"center\">结果\u003C\u002Fp>\n\n## :clap: 完成了！\n如有任何疑问或咨询，欢迎随时邮件联系我\n:email: chandrikadeb7@gmail.com\n\n---\n\n## 物联网 (Internet of Things) 设备设置\n\n### 预期硬件\n* [带外壳的 Raspberry Pi (树莓派) 4 4GB](https:\u002F\u002Fwww.canakit.com\u002Fraspberry-pi-4-4gb.html)\n* [来自 Arducam 的 5MP OV5647 PiCamera](https:\u002F\u002Fwww.arducam.com\u002Fdocs\u002Fcameras-for-raspberry-pi\u002Fnative-raspberry-pi-cameras\u002F5mp-ov5647-cameras\u002F)\n\n### 入门指南\n* 按照 `documentation\u002FCanaKit-Raspberry-Pi-Quick-Start-Guide-4.0.pdf` 第 3 页或 https:\u002F\u002Fwww.canakit.com\u002FMedia\u002FCanaKit-Raspberry-Pi-Quick-Start-Guide-4.0.pdf 中的“入门指南”部分设置 Raspberry Pi (树莓派) 外壳和操作系统 (Operating System)\n  * 使用 NOOBS 时，请选择推荐的操作系统\n* 设置 PiCamera\n  * 使用 `documentation\u002FArducam-Case-Setup.pdf` 或 https:\u002F\u002Fwww.arducam.com\u002Fdocs\u002Fcameras-for-raspberry-pi\u002Fnative-raspberry-pi-cameras\u002F5mp-ov5647-cameras\u002F 组装 Arducam 的 PiCamera 外壳\n  * [将您的 PiCamera 模块连接到 Raspberry Pi 并启用摄像头](https:\u002F\u002Fprojects.raspberrypi.org\u002Fen\u002Fprojects\u002Fgetting-started-with-picamera\u002F2)\n\n### Raspberry Pi 应用安装与执行\n\n> 克隆项目后运行这些命令\n\n| 命令                                                                                                                     | 完成时间 |\n|------------------------------------------------------------------------------------------------------------------------------|--------------------|\n| sudo apt install -y libatlas-base-dev liblapacke-dev gfortran                                                                | 1 分钟               |\n| sudo apt install -y libhdf5-dev libhdf5-103                                                                                  | 1 分钟               |\n| pip3 install -r requirements.txt                                                                                             | 1-3 分钟           |\n| wget \"https:\u002F\u002Fraw.githubusercontent.com\u002FPINTO0309\u002FTensorflow-bin\u002Fmaster\u002Ftensorflow-2.4.0-cp37-none-linux_armv7l_download.sh\" | 少于 10 秒  |\n| .\u002Ftensorflow-2.4.0-cp37-none-linux_armv7l_download.sh                                                                        | 少于 10 秒  |\n| pip3 install tensorflow-2.4.0-cp37-none-linux_armv7l.whl                                                                     | 1-3 分钟           |\n\n---\n\n## :trophy: 奖项\n在 [Amdocs Innovation India ICE Project Fair]( https:\u002F\u002Fwww.amdocs.com\u002F) 中获得亚军席位\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_0cad02888e08.jpeg)\n\n## :raising_hand: 引用来源：\n\n1. https:\u002F\u002Fosf.io\u002Fpreprints\u002F3gph4\u002F\n2. https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-981-33-4673-4_49\n3. https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9312083\u002F\n4. https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-981-33-4673-4_48\n5. https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FAkhyar_Ahmed\u002Fpublication\u002F344173985_Face_Mask_Detector\u002Flinks\u002F5f58c00ea6fdcc9879d8e6f7\u002FFace-Mask-Detector.pdf\n\n## 👏 致谢\n\n### 入选 [Devscript Winter Of Code](https:\u002F\u002Fdevscript.tech\u002Fwoc\u002F)\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_fce0ea79a152.jpeg\" height=300 width=300>\n\n### 入选 [Script Winter Of Code](https:\u002F\u002Fswoc.tech\u002Fproject.html)\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_a18b127a4462.jpeg\" height=300 width=300>\n\n### 入选 [Student Code-in](https:\u002F\u002Fscodein.tech\u002F)\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_9a714af583ac.jpeg\" height=300 width=300>\n\n## :+1: 鸣谢\n* [https:\u002F\u002Fwww.pyimagesearch.com\u002F](https:\u002F\u002Fwww.pyimagesearch.com\u002F)\n* [https:\u002F\u002Fwww.tensorflow.org\u002Ftutorials\u002Fimages\u002Ftransfer_learning](https:\u002F\u002Fwww.tensorflow.org\u002Ftutorials\u002Fimages\u002Ftransfer_learning)\n\n## :handshake: 贡献\n\n#### 请在此阅读贡献指南 [此处](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fblob\u002Fmaster\u002FCONTRIBUTING.md)\n欢迎在 [Face-Mask-Detection](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fissues) 仓库中**提交新议题**，附带相应的标题和描述。如果您已经找到了解决方案，**我非常乐意审查您的拉取请求**! \n\n## :handshake: 我们的贡献者\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_readme_59a96664b1e4.png\" \u002F>\n\u003C\u002Fa>\n\n\n## :eyes: 行为准则\n\n您可以在 [此处](\u002FCODE_OF_CONDUCT.md) 找到我们的行为准则。\n\n## :heart: 作者\n由 [Chandrika Deb](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7) 用心制作 :heart:&nbsp;\n\n## :eyes: 许可证\nMIT © [Chandrika Deb](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fblob\u002Fmaster\u002FLICENSE)","# Face-Mask-Detection 快速上手指南\n\n## 简介\n本项目是一个基于 OpenCV、Keras\u002FTensorFlow 和深度学习的口罩检测系统。支持在静态图像及实时视频流中检测面部是否佩戴口罩。模型采用 MobileNetV2 架构，计算高效，适合嵌入式系统部署。\n\n## 环境准备\n- **操作系统**: Linux \u002F macOS \u002F Windows\n- **Python 版本**: 3.6+\n- **依赖库**: 详见项目根目录下的 `requirements.txt`\n- **硬件建议**: 推荐使用 NVIDIA GPU 以加速训练（需安装 CUDA\u002FcuDNN）\n\n## 安装步骤\n1. **克隆仓库**\n   ```bash\n   $ git clone https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection.git\n   ```\n   *(提示：国内网络环境下建议使用 Gitee 镜像或配置代理以提升下载速度)*\n\n2. **进入项目目录**\n   ```bash\n   $ cd Face-Mask-Detection\n   ```\n\n3. **创建并激活虚拟环境**\n   ```bash\n   $ virtualenv test\n   $ source test\u002Fbin\u002Factivate\n   ```\n\n4. **安装依赖库**\n   ```bash\n   $ pip3 install -r requirements.txt\n   ```\n\n## 基本使用\n\n### 1. 训练模型\n确保已准备好数据集（位于 `dataset` 目录下），运行以下命令进行训练：\n```bash\n$ python3 train_mask_detector.py --dataset dataset\n```\n\n### 2. 检测图片\n对单张静态图像进行口罩检测：\n```bash\n$ python3 detect_mask_image.py --image images\u002Fpic1.jpeg\n```\n\n### 3. 检测视频流\n调用摄像头进行实时视频流口罩检测：\n```bash\n$ python3 detect_mask_video.py \n```\n\n### 4. Web 应用 (Streamlit)\n如需通过浏览器访问检测界面，可启动 Streamlit 应用：\n```bash\n$ streamlit run app.py \n```\n\n## 数据集说明\n项目使用的数据集包含 4095 张图片（有口罩 2165 张，无口罩 1930 张）。\n下载地址：[Click to Download](https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Ftree\u002Fmaster\u002Fdataset)\n\n---\n*注：模型在 tensorflow-gpu==2.5.0 环境下训练可获得约 98% 的准确率。*","某大型科技园区安保团队需在早晚高峰时段，对进出大楼的所有人员进行严格的口罩佩戴合规性监控。\n\n### 没有 Face-Mask-Detection 时\n- 保安需全程紧盯监控屏幕，长时间工作易疲劳导致漏检率高达 20%。\n- 发现违规只能口头提醒，无法留存影像证据进行后续数据分析。\n- 高峰期人流密集，人工排查造成门口拥堵，严重影响通行效率。\n- 恶劣天气或逆光条件下，肉眼判断极易出现误判，引发纠纷。\n\n### 使用 Face-Mask-Detection 后\n- 系统实时捕捉视频流画面，自动框选人脸并判定口罩状态，实现毫秒级响应。\n- 违规记录自动生成电子台账，支持按时间段导出报表供管理层查看决策。\n- 实现无感通行，闸机联动控制，大幅减少人员聚集等待时间与接触风险。\n- 采用轻量化模型部署，在普通摄像头下依然能稳定识别，适应多种复杂光照环境。\n\n通过引入自动化视觉检测技术，园区成功实现了从传统人力密集型监管向智能化精准防控体系的根本转型。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fchandrikadeb7_Face-Mask-Detection_064612bc.png","chandrikadeb7","Chandrika Deb","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fchandrikadeb7_75059398.jpg","Software Engineer at Amdocs | Content Freelancer | Innovation Agent | Learning Golang!","Amdocs","Jamshedpur, India","chandrikadeb7@gmail.com","https:\u002F\u002Fchandrikadeb7.github.io","https:\u002F\u002Fgithub.com\u002Fchandrikadeb7",[85,89,92],{"name":86,"color":87,"percentage":88},"Jupyter Notebook","#DA5B0B",98,{"name":90,"color":91,"percentage":23},"Python","#3572A5",{"name":93,"color":94,"percentage":95},"CSS","#663399",0,1605,863,"2026-04-03T08:37:36","MIT","未说明","非必需，训练建议使用 GPU (tensorflow-gpu)，具体型号\u002F显存\u002FCUDA 版本未说明",{"notes":103,"python":104,"dependencies":105},"需手动下载数据集；支持在树莓派等嵌入式设备上运行；Web 应用基于 Streamlit；训练模型精度约 98%，依赖 tensorflow-gpu 2.5.0","3.6+",[106,107,108,109,110],"opencv","keras","tensorflow","caffe","streamlit",[13,14],[113,114,115,107,116,117,118,119,120,121,122,123,124,125,126,127,128,129,109,130],"python","python-3","python3","keras-tensorflow","deep-learning","computer-vision","face-mask-detection","covid-19","ssd-mobilenet","mobilenetv2","bing-search","mask-detection","facemaskdetect","facemask-detection","mask-detection-system","face-mask","machine-learning","hacktoberfest",null,"2026-03-27T02:49:30.150509","2026-04-06T08:52:31.420103",[135,140,145,150,155,160],{"id":136,"question_zh":137,"answer_zh":138,"source_url":139},2632,"如何在树莓派（Raspberry Pi）上运行该项目？","建议使用 Raspbian 32-bit 操作系统。如果遇到 TensorFlow 问题，请尝试使用最新提交的代码，因为新的 requirements.txt 文件已修复相关问题。","https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fissues\u002F117",{"id":141,"question_zh":142,"answer_zh":143,"source_url":144},2633,"实时视频中为什么无法检测多张人脸？","当前模型可能不支持多目标检测。根据维护者回复，需要切换到 YOLOv3 模型才能在实时流中检测多张人脸。","https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fissues\u002F1",{"id":146,"question_zh":147,"answer_zh":148,"source_url":149},2634,"如何查找并添加该项目的学术引用链接？","请在 Google Scholar 等平台上搜索该仓库的引用，找到相关的研究论文后，将链接添加到 Readme 文件的 Cited By 部分。","https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fissues\u002F112",{"id":151,"question_zh":152,"answer_zh":153,"source_url":154},2635,"贡献者任务是如何分配的？","维护者通常要求先完成已分配的任务后再分配新任务。例如，有用户请求分配任务时，被要求先完成现有任务。","https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fissues\u002F77",{"id":156,"question_zh":157,"answer_zh":158,"source_url":159},2636,"如何向数据集文件夹添加彩色口罩图片？","可以联系维护者申请解决此问题。通常需要说明计划添加的图片数量和颜色（如蓝色、粉色等），并根据现有贡献者的选择避免重复颜色。","https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fissues\u002F51",{"id":161,"question_zh":162,"answer_zh":163,"source_url":164},2637,"是否可以使用 Inception V3 架构训练模型？","是的，Inception V3 可以提供更好的准确率。用户可以申请处理相关任务，但需注意进度可能会因个人情况有所延迟。","https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fissues\u002F71",[166],{"id":167,"version":168,"summary_zh":169,"released_at":170},111810,"v1.0.0","## What's Changed\r\n* Add Muthu-Annamalai to README.md by @muthuannamalai12 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F65\r\n* Add Muthu Annamalai by @muthuannamalai12 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F68\r\n* Vilsi12 patch 2 by @vilsi12 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F70\r\n* Awards new by @vilsi12 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F64\r\n* Added images in the dataset. by @keshav340 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F69\r\n* Added new images in the dataset by @vaishnavi-1 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F60\r\n* YouTube demo link updated. by @Purvanshsingh in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F76\r\n* Added config file for Welcome BOT by @muthuannamalai12 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F79\r\n* Add Issue Template by @muthuannamalai12 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F82\r\n* Created an MIT License for Face-Mask-Detection by @shubhraagarwal in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F83\r\n* Add templates for pull request by @muthuannamalai12 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F93\r\n* Update Web App theme and styling by @IndraP24 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F89\r\n* Alarm system when No Mask detected by @sahebsunny in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F87\r\n* Face Mask Detection using ResNet50 v2 by @RaghavModi in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F100\r\n* Added Citation Section by @Sobhit25 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F99\r\n* Issue #75 : Insertion of Google Colab link in the readme by @TanweerulHaque in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F103\r\n* Added notification pop up by @Aayush-hub in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F102\r\n* INCEPTION_V3 MODEL VISUALISATION ISSUE#71 by @spursbyte in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F104\r\n* Updated contributor's.md file by @Amit366 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F105\r\n* Added guide to set up project on Windows by @kritikaparmar-programmer in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F107\r\n* Added Github Action by @Aayush-hub in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F108\r\n* Updated number of images in readme of datasets by @jatinjain001 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F110\r\n* Fixed broken README.md File Link in Windows_guide.md by @BhendiBoi in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F115\r\n* Added GitHub action to auto-assign mentor by @m-code12 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F116\r\n* Added a 'Cited by' section in README.md file. by @anirudhsai20 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F121\r\n* Added Logo by @Vrushti24 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F118\r\n* Update Windows_guide.md by @AmeyaUpalanchi in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F122\r\n* Bump pillow from 7.2.0 to 8.1.1 by @dependabot in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F123\r\n* Add support installation instruction for Raspberry Pi by @vinamramunot-tech in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F128\r\n* Frame crash issue resolved by @ritikchinu in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F140\r\n* updated app.py (solves #144) by @sreyan-ghosh in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F145\r\n* Create CONTRIBUTING.md file for new contributors by @chandrikadeb7 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F148\r\n* Update README.md by @chandrikadeb7 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F149\r\n* Updated README.md by @royshreyaaa in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F153\r\n* Add README.md file in Korean by @seokkim0130 in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F159\r\n* Add export to ONNX by @SthPhoenix in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F161\r\n\r\n## New Contributors\r\n* @muthuannamalai12 made their first contribution in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F65\r\n* @vilsi12 made their first contribution in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F70\r\n* @keshav340 made their first contribution in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F69\r\n* @vaishnavi-1 made their first contribution in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F60\r\n* @Purvanshsingh made their first contribution in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F76\r\n* @shubhraagarwal made their first contribution in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F83\r\n* @IndraP24 made their first contribution in https:\u002F\u002Fgithub.com\u002Fchandrikadeb7\u002FFace-Mask-Detection\u002Fpull\u002F89\r\n* @sahebsu","2022-02-27T07:27:37"]