[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-HeroKillerEver--coursera-deep-learning":3,"tool-HeroKillerEver--coursera-deep-learning":65},[4,23,32,40,49,57],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":22},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。",85092,2,"2026-04-10T11:13:16",[13,14,15,16,17,18,19,20,21],"图像","数据工具","视频","插件","Agent","其他","语言模型","开发框架","音频","ready",{"id":24,"name":25,"github_repo":26,"description_zh":27,"stars":28,"difficulty_score":29,"last_commit_at":30,"category_tags":31,"status":22},5784,"funNLP","fighting41love\u002FfunNLP","funNLP 是一个专为中文自然语言处理（NLP）打造的超级资源库，被誉为\"NLP 民工的乐园”。它并非单一的软件工具，而是一个汇集了海量开源项目、数据集、预训练模型和实用代码的综合性平台。\n\n面对中文 NLP 领域资源分散、入门门槛高以及特定场景数据匮乏的痛点，funNLP 提供了“一站式”解决方案。这里不仅涵盖了分词、命名实体识别、情感分析、文本摘要等基础任务的标准工具，还独特地收录了丰富的垂直领域资源，如法律、医疗、金融行业的专用词库与数据集，甚至包含古诗词生成、歌词创作等趣味应用。其核心亮点在于极高的全面性与实用性，从基础的字典词典到前沿的 BERT、GPT-2 模型代码，再到高质量的标注数据和竞赛方案，应有尽有。\n\n无论是刚刚踏入 NLP 领域的学生、需要快速验证想法的算法工程师，还是从事人工智能研究的学者，都能在这里找到急需的“武器弹药”。对于开发者而言，它能大幅减少寻找数据和复现模型的时间；对于研究者，它提供了丰富的基准测试资源和前沿技术参考。funNLP 以开放共享的精神，极大地降低了中文自然语言处理的开发与研究成本，是中文 AI 社区不可或缺的宝藏仓库。",79857,1,"2026-04-08T20:11:31",[19,14,18],{"id":33,"name":34,"github_repo":35,"description_zh":36,"stars":37,"difficulty_score":29,"last_commit_at":38,"category_tags":39,"status":22},5773,"cs-video-courses","Developer-Y\u002Fcs-video-courses","cs-video-courses 是一个精心整理的计算机科学视频课程清单，旨在为自学者提供系统化的学习路径。它汇集了全球知名高校（如加州大学伯克利分校、新南威尔士大学等）的完整课程录像，涵盖从编程基础、数据结构与算法，到操作系统、分布式系统、数据库等核心领域，并深入延伸至人工智能、机器学习、量子计算及区块链等前沿方向。\n\n面对网络上零散且质量参差不齐的教学资源，cs-video-courses 解决了学习者难以找到成体系、高难度大学级别课程的痛点。该项目严格筛选内容，仅收录真正的大学层级课程，排除了碎片化的简短教程或商业广告，确保用户能接触到严谨的学术内容。\n\n这份清单特别适合希望夯实计算机基础的开发者、需要补充特定领域知识的研究人员，以及渴望像在校生一样系统学习计算机科学的自学者。其独特的技术亮点在于分类极其详尽，不仅包含传统的软件工程与网络安全，还细分了生成式 AI、大语言模型、计算生物学等新兴学科，并直接链接至官方视频播放列表，让用户能一站式获取高质量的教育资源，免费享受世界顶尖大学的课堂体验。",79792,"2026-04-08T22:03:59",[18,13,14,20],{"id":41,"name":42,"github_repo":43,"description_zh":44,"stars":45,"difficulty_score":46,"last_commit_at":47,"category_tags":48,"status":22},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。",77062,3,"2026-04-04T04:44:48",[17,13,20,19,18],{"id":50,"name":51,"github_repo":52,"description_zh":53,"stars":54,"difficulty_score":46,"last_commit_at":55,"category_tags":56,"status":22},519,"PaddleOCR","PaddlePaddle\u002FPaddleOCR","PaddleOCR 是一款基于百度飞桨框架开发的高性能开源光学字符识别工具包。它的核心能力是将图片、PDF 等文档中的文字提取出来，转换成计算机可读取的结构化数据，让机器真正“看懂”图文内容。\n\n面对海量纸质或电子文档，PaddleOCR 解决了人工录入效率低、数字化成本高的问题。尤其在人工智能领域，它扮演着连接图像与大型语言模型（LLM）的桥梁角色，能将视觉信息直接转化为文本输入，助力智能问答、文档分析等应用场景落地。\n\nPaddleOCR 适合开发者、算法研究人员以及有文档自动化需求的普通用户。其技术优势十分明显：不仅支持全球 100 多种语言的识别，还能在 Windows、Linux、macOS 等多个系统上运行，并灵活适配 CPU、GPU、NPU 等各类硬件。作为一个轻量级且社区活跃的开源项目，PaddleOCR 既能满足快速集成的需求，也能支撑前沿的视觉语言研究，是处理文字识别任务的理想选择。",75489,"2026-04-13T11:13:28",[19,13,20,18],{"id":58,"name":59,"github_repo":60,"description_zh":61,"stars":62,"difficulty_score":29,"last_commit_at":63,"category_tags":64,"status":22},3215,"awesome-machine-learning","josephmisiti\u002Fawesome-machine-learning","awesome-machine-learning 是一份精心整理的机器学习资源清单，汇集了全球优秀的机器学习框架、库和软件工具。面对机器学习领域技术迭代快、资源分散且难以甄选的痛点，这份清单按编程语言（如 Python、C++、Go 等）和应用场景（如计算机视觉、自然语言处理、深度学习等）进行了系统化分类，帮助使用者快速定位高质量项目。\n\n它特别适合开发者、数据科学家及研究人员使用。无论是初学者寻找入门库，还是资深工程师对比不同语言的技术选型，都能从中获得极具价值的参考。此外，清单还延伸提供了免费书籍、在线课程、行业会议、技术博客及线下聚会等丰富资源，构建了从学习到实践的全链路支持体系。\n\n其独特亮点在于严格的维护标准：明确标记已停止维护或长期未更新的项目，确保推荐内容的时效性与可靠性。作为机器学习领域的“导航图”，awesome-machine-learning 以开源协作的方式持续更新，旨在降低技术探索门槛，让每一位从业者都能高效地站在巨人的肩膀上创新。",72149,"2026-04-03T21:50:24",[20,18],{"id":66,"github_repo":67,"name":68,"description_en":69,"description_zh":70,"ai_summary_zh":71,"readme_en":72,"readme_zh":73,"quickstart_zh":74,"use_case_zh":75,"hero_image_url":76,"owner_login":77,"owner_name":78,"owner_avatar_url":79,"owner_bio":80,"owner_company":81,"owner_location":82,"owner_email":83,"owner_twitter":84,"owner_website":85,"owner_url":86,"languages":87,"stars":96,"forks":97,"last_commit_at":98,"license":84,"difficulty_score":29,"env_os":99,"env_gpu":100,"env_ram":100,"env_deps":101,"category_tags":104,"github_topics":84,"view_count":10,"oss_zip_url":84,"oss_zip_packed_at":84,"status":22,"created_at":105,"updated_at":106,"faqs":107,"releases":108},7164,"HeroKillerEver\u002Fcoursera-deep-learning","coursera-deep-learning","Solutions to all quiz and all the programming assignments!!!","coursera-deep-learning 是一个专为吴恩达教授（Andrew Ng）在 deeplearning.ai 推出的深度学习专项课程打造的开源学习资源库。它完整收录了课程中所有周次的测验答案与编程作业代码，涵盖从神经网络基础、深层网络构建，到超参数调优、正则化、优化算法及 TensorFlow 实战等核心内容。\n\n对于正在修读该系列课程的学习者而言，coursera-deep-learning 有效解决了自学过程中遇到的代码调试困难和思路卡点问题。当用户在实现复杂的反向传播或梯度检查时遇到瓶颈，可以参考这里的标准实现来验证逻辑；在完成测验后，也能通过对照答案加深对理论知识的理解。需要强调的是，创建者初衷是将其作为学术参考与交流媒介，旨在帮助学习者更好地掌握知识，而非鼓励直接抄袭。\n\n这款资源库特别适合计算机专业的学生、AI 领域的初学者以及希望系统夯实深度学习基础的开发者使用。其独特的价值在于提供了“手把手”式的步骤化代码实现（Step by Step），将抽象的数学公式转化为可运行的 Python 代码，极大地降低了入门门槛。无论是为了完成课程作业，还是作为未来项目开发","coursera-deep-learning 是一个专为吴恩达教授（Andrew Ng）在 deeplearning.ai 推出的深度学习专项课程打造的开源学习资源库。它完整收录了课程中所有周次的测验答案与编程作业代码，涵盖从神经网络基础、深层网络构建，到超参数调优、正则化、优化算法及 TensorFlow 实战等核心内容。\n\n对于正在修读该系列课程的学习者而言，coursera-deep-learning 有效解决了自学过程中遇到的代码调试困难和思路卡点问题。当用户在实现复杂的反向传播或梯度检查时遇到瓶颈，可以参考这里的标准实现来验证逻辑；在完成测验后，也能通过对照答案加深对理论知识的理解。需要强调的是，创建者初衷是将其作为学术参考与交流媒介，旨在帮助学习者更好地掌握知识，而非鼓励直接抄袭。\n\n这款资源库特别适合计算机专业的学生、AI 领域的初学者以及希望系统夯实深度学习基础的开发者使用。其独特的价值在于提供了“手把手”式的步骤化代码实现（Step by Step），将抽象的数学公式转化为可运行的 Python 代码，极大地降低了入门门槛。无论是为了完成课程作业，还是作为未来项目开发的代码模板，coursera-deep-learning 都是一位忠实且专业的“伴读助手”，陪伴你轻松跨越深度学习的学习曲线。","\u003Cp align=\"center\">\u003Cimg width=\"40%\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FHeroKillerEver_coursera-deep-learning_readme_aac5e7e0a050.png\" \u002F>\u003C\u002Fp>\n\n--------------------------------------------------------------------------------\n\nA series of online courses offered by [deeplearning.ai](https:\u002F\u002Fwww.deeplearning.ai\u002F). I would like to say thanks to Prof. [**Andrew Ng**](www.andrewng.org) and his colleagues for spreading knowledge to normal people and great courses sincerely.  \n\n\n### Reminder\n-------------------\nThe reason I would like to create this repository is purely for academic use (in case for my future use). I am really glad if you can use it as a reference and happy to discuss with you about issues related with the course even for further deep learning techniques. \n\n**Please only use it as a reference**. The quiz and assignments are relatively easy to answer, hope you can have fun with the courses.  \n\n\n### 1. Neural Network and Deep Learning\n* Week 1\n\t* [Quiz 1](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002Fweek1%20quiz.md)\n\t* [Logistic Regression as a Neural Network](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002FLogistic%20Regression%20as%20a%20Neural%20Network)\n\n* Week 2\n\t* [Quiz 2](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002Fweek2%20quiz.md)\n\t* [Logistic Regression as a Neural Network](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002FLogistic%20Regression%20as%20a%20Neural%20Network)\n\n* Week 3\n\t* [Quiz 3](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002Fweek3%20quiz.md)\n\t* [Building your Deep Neural Network - Step by Step](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002FBuilding%20your%20Deep%20Neural%20Network%20-%20Step%20by%20Step)\n\t* [Deep Neural Network Application-Image Classification](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002FDeep%20Neural%20Network%20Application-Image%20Classification)\n\n### 2. Improving Deep Neural Networks-Hyperparameter tuning, Regularization and Optimization\n* Week 1\n\t* [Quiz 1](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002Fweek1%20quiz.md)\n\t* [Initialization](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FInitialization)\n\t* [Regularization](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FRegularization)\n\t* [Gradient Checking](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FGradient%20Checking)\n\n* Week 2\n\t* [Quiz 2](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002Fweek2%20quiz.md)\n\t* [Optimization](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FOptimization)\n\n* Week 3\n\t* [Quiz 3](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002Fweek3%20quiz.md) \n\t* [Tensorflow](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FTensorflow)\n\n### 3. Structuring Machine Learning Projects\n* Week 1\n\t* [Quiz 1](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FStructuring%20Machine%20Learning%20Projects\u002Fweek1%20quiz.md)\n\n* Week 2\n\t* [Quiz 2](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FStructuring%20Machine%20Learning%20Projects\u002Fweek2%20quiz.md)\n\n### 4. Convolutional Neural Network\n* Week 1\n\t* [Quiz 1](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002Fweek1%20quiz.md)\n\t* [Convolutional Model- step by step](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002FConvolutional%20Model-%20step%20by%20step)\n\n* Week 2\n\t* [Quiz 2](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002Fweek2%20quiz.md)\n\t* [ResNets](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002FResNets)\n\n* Week 3\n\t* [Quiz 3](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002Fweek3%20quiz.md)\n\t* [Car detection for Autonomous Driving](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002FCar%20detection%20for%20Autonomous%20Driving)\n\n* Week 4\n\t* [Quiz 4](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002Fweek4%20quiz.md)\n\t* [Neural Style Transfer](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002FNeural%20Style%20Transfer)\n\t* [Face Recognition](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002FFace%20Recognition)\n\n\n### 5. Sequence Models\n* Week 1\n\t* [Quiz 1](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002Fweek1%20quiz.md)\n\t* [Building a Recurrent Neural Network - Step by Step](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FBuilding%20a%20Recurrent%20Neural%20Network%20-%20Step%20by%20Step)\n\t* [Dinosaur Island -- Character-level language model](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FDinosaur%20Island%20--%20Character-level%20language%20model)\n\t* [Jazz improvisation with LSTM](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FJazz%20improvisation%20with%20LSTM)\n\n* Week 2\n\t* [Quiz 2](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002Fweek2%20quiz.md)\n\t* [Word Vector Representation](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FWord%20Vector%20Representation)\n\t* [Emojify](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FEmojify)\n\n* Week 3\n\t* [Quiz 3](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002Fweek3%20quiz.md)\n\t* [Machine Translation](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FMachine%20Translation)\n\t* [Trigger Word Detection](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FTrigger%20word%20detection)\n\n\n\u003Cbr\u002F>\n\n\n### Author\nHaibin Yu\u002F [@HeroKillerEver](https:\u002F\u002Fgithub.com\u002FHeroKillerEver)\n","\u003Cp align=\"center\">\u003Cimg width=\"40%\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FHeroKillerEver_coursera-deep-learning_readme_aac5e7e0a050.png\" \u002F>\u003C\u002Fp>\n\n--------------------------------------------------------------------------------\n\n由[deeplearning.ai](https:\u002F\u002Fwww.deeplearning.ai\u002F)提供的系列在线课程。我要衷心感谢[**吴恩达**](www.andrewng.org)教授及其团队，他们将知识无私地分享给大众，并提供了非常优秀的课程。\n\n\n### 提醒\n-------------------\n我创建这个仓库的初衷纯粹是为了学术用途（以备将来参考）。如果你能将其作为参考资料，我将不胜欣喜；同时我也很乐意与你讨论课程相关的问题，甚至是更深入的深度学习技术。\n\n**请仅将其作为参考使用**。测验和作业相对容易解答，希望你能享受这些课程的学习过程。  \n\n\n### 1. 神经网络与深度学习\n* 第一周\n\t* [测验1](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002Fweek1%20quiz.md)\n\t* [逻辑回归作为神经网络](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002FLogistic%20Regression%20as%20a%20Neural%20Network)\n\n* 第二周\n\t* [测验2](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002Fweek2%20quiz.md)\n\t* [逻辑回归作为神经网络](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002FLogistic%20Regression%20as%20a%20Neural%20Network)\n\n* 第三周\n\t* [测验3](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002Fweek3%20quiz.md)\n\t* [构建你的深度神经网络——逐步详解](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002FBuilding%20your%20Deep%20Neural%20Network%20-%20Step%20by%20Step)\n\t* [深度神经网络应用——图像分类](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FNeural%20Networks%20and%20Deep%20Learning\u002FDeep%20Neural%20Network%20Application-Image%20Classification)\n\n### 2. 改进深度神经网络——超参数调优、正则化与优化\n* 第一周\n\t* [测验1](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002Fweek1%20quiz.md)\n\t* [参数初始化](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FInitialization)\n\t* [正则化](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FRegularization)\n\t* [梯度检验](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FGradient%20Checking)\n\n* 第二周\n\t* [测验2](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002Fweek2%20quiz.md)\n\t* [优化算法](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FOptimization)\n\n* 第三周\n\t* [测验3](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002Fweek3%20quiz.md) \n\t* [TensorFlow](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FImproving%20Deep%20Neural%20Networks-Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FTensorflow)\n\n### 3. 机器学习项目结构设计\n* 第一周\n\t* [测验1](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FStructuring%20Machine%20Learning%20Projects\u002Fweek1%20quiz.md)\n\n* 第二周\n\t* [测验2](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Fblob\u002Fmaster\u002FStructuring%20Machine%20Learning%20Projects\u002Fweek2%20quiz.md)\n\n### 4. 卷积神经网络\n* 第一周\n\t* [测验1](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002Fweek1%20quiz.md)\n\t* [卷积模型——逐步详解](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002FConvolutional%20Model-%20step%20by%20step)\n\n* 第二周\n\t* [测验2](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002Fweek2%20quiz.md)\n\t* [ResNet](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002FResNets)\n\n* 第三周\n\t* [测验3](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002Fweek3%20quiz.md)\n\t* [自动驾驶中的车辆检测](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002FCar%20detection%20for%20Autonomous%20Driving)\n\n* 第四周\n\t* [测验4](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002Fweek4%20quiz.md)\n\t* [神经风格迁移](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002FNeural%20Style%20Transfer)\n\t* [人脸识别](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FConvolutional%20Neural%20Networks\u002FFace%20Recognition)\n\n### 5. 序列模型\n* 第1周\n\t* [测验1](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002Fweek1%20quiz.md)\n\t* [循序渐进构建循环神经网络](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FBuilding%20a%20Recurrent%20Neural%20Network%20-%20Step%20by%20Step)\n\t* [恐龙岛——字符级语言模型](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FDinosaur%20Island%20--%20Character-level%20language%20model)\n\t* [使用LSTM即兴演奏爵士乐](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FJazz%20improvisation%20with%20LSTM)\n\n* 第2周\n\t* [测验2](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002Fweek2%20quiz.md)\n\t* [词向量表示](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FWord%20Vector%20Representation)\n\t* [表情符号生成器](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FEmojify)\n\n* 第3周\n\t* [测验3](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002Fweek3%20quiz.md)\n\t* [机器翻译](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FMachine%20Translation)\n\t* [触发词检测](https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FTrigger%20word%20detection)\n\n\n\u003Cbr\u002F>\n\n\n### 作者\n于海彬 \u002F [@HeroKillerEver](https:\u002F\u002Fgithub.com\u002FHeroKillerEver)","# Coursera 深度学习专项课程资源快速上手指南\n\n本仓库整理了吴恩达（Andrew Ng）教授在 Coursera 上开设的 [deeplearning.ai](https:\u002F\u002Fwww.deeplearning.ai) 深度学习专项课程的测验答案与编程作业参考代码。本指南旨在帮助开发者快速定位并运行相关实验代码。\n\n> **⚠️ 重要提示**：本资源仅供学术参考与交流。请勿直接复制提交作业，建议先独立完成练习以巩固知识。\n\n## 1. 环境准备\n\n### 系统要求\n- **操作系统**：Windows \u002F macOS \u002F Linux\n- **Python 版本**：推荐 Python 3.6 - 3.8（部分旧版作业可能不兼容最新 Python 3.10+）\n- **包管理器**：pip 或 conda\n\n### 前置依赖\n主要依赖以下科学计算与深度学习库：\n- `numpy`\n- `matplotlib`\n- `h5py`\n- `scipy`\n- `Pillow` (PIL)\n- `tensorflow` (部分课程涉及 TF 1.x 或 2.x，请注意对应版本)\n- `keras`\n\n## 2. 安装步骤\n\n### 第一步：克隆仓库\n使用 Git 将项目代码拉取到本地：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning.git\ncd coursera-deep-learning\n```\n\n*国内用户若下载缓慢，可使用 Gitee 镜像（如有）或通过代理加速。*\n\n### 第二步：创建虚拟环境（推荐）\n为避免依赖冲突，建议使用 Conda 或 venv 创建独立环境：\n\n```bash\n# 使用 conda 创建名为 dl-course 的环境\nconda create -n dl-course python=3.7\nconda activate dl-course\n```\n\n### 第三步：安装依赖库\n进入具体的课程文件夹后安装所需包。由于不同周次的作业依赖略有差异，建议先安装通用基础包：\n\n```bash\npip install numpy matplotlib h5py scipy pillow\n```\n\n若运行 **Course 2 Week 3** 或后续涉及 TensorFlow 的作业，请安装对应版本：\n\n```bash\n# 针对较新作业 (TensorFlow 2.x)\npip install tensorflow\n\n# 若遇到旧版代码报错，可能需要安装特定旧版本 (如 TF 1.15)\n# pip install tensorflow==1.15\n```\n\n## 3. 基本使用\n\n本仓库按课程章节分类，结构如下：\n1. **Neural Networks and Deep Learning** (神经网络与深度学习)\n2. **Improving Deep Neural Networks** (改善深层神经网络)\n3. **Structuring Machine Learning Projects** (结构化机器学习项目)\n4. **Convolutional Neural Networks** (卷积神经网络)\n5. **Sequence Models** (序列模型)\n\n### 运行示例\n以 **Course 1 Week 3: Building your Deep Neural Network** 为例：\n\n1. **进入对应目录**：\n   ```bash\n   cd \"Neural Networks and Deep Learning\u002FBuilding your Deep Neural Network - Step by Step\"\n   ```\n\n2. **查看文件结构**：\n   通常包含 `.ipynb` (Jupyter Notebook) 文件和辅助数据文件。\n\n3. **启动 Jupyter Notebook**：\n   ```bash\n   jupyter notebook\n   ```\n\n4. **执行代码**：\n   - 在浏览器中打开对应的 `.ipynb` 文件。\n   - 按照单元格顺序依次运行（Shift + Enter）。\n   - 参考 `dnn_utils_v2.py` 或 `testCases_v3.py` 等辅助脚本理解函数逻辑。\n\n### 其他课程快速索引\n- **CNN 汽车检测**：`cd \"Convolutional Neural Networks\u002FCar detection for Autonomous Driving\"`\n- **RNN 恐龙岛生成**：`cd \"Sequence Models\u002FDinosaur Island -- Character-level language model\"`\n- **神经风格迁移**：`cd \"Convolutional Neural Networks\u002FNeural Style Transfer\"`\n\n---\n*作者：Haibin Yu (@HeroKillerEver)*\n*原项目地址：https:\u002F\u002Fgithub.com\u002FHeroKillerEver\u002Fcoursera-deep-learning*","一名刚转行深度学习的数据分析师正在自学吴恩达教授的 Coursera 专项课程，试图通过编程作业掌握神经网络构建与超参数调优的核心技能。\n\n### 没有 coursera-deep-learning 时\n- 在编写“从零构建深度神经网络”作业时，因反向传播公式推导复杂，代码调试陷入死循环，耗费数天仍无法定位梯度计算错误。\n- 面对模型过拟合问题，不清楚如何正确实施 L2 正则化或 Dropout，反复试错导致学习进度严重滞后，挫败感强烈。\n- 遇到测验中的概念陷阱（如优化算法选择）时缺乏即时参考，只能盲目搜索碎片化信息，难以验证自己理解的正确性。\n- 担心因一个小 bug 卡住而放弃整个课程，甚至产生抄袭完整代码的冲动，违背了初衷却无可奈何。\n\n### 使用 coursera-deep-learning 后\n- 遇到梯度检查报错时，直接对照仓库中\"Gradient Checking\"的实现逻辑，迅速发现维度不匹配问题，将调试时间从几天缩短至半小时。\n- 在调优环节参考\"Regularization\"和\"Optimization\"的标准解法，清晰理解了不同正则化手段的代码落地方式，成功将测试集准确率提升至预期水平。\n- 完成编程任务后，利用提供的 Quiz 解析作为“标准答案”进行自测，快速纠正了对动量梯度下降等概念的误解，巩固了理论基础。\n- 将其作为严格的“参考指南”而非复制源，在确保独立思考的前提下高效扫清障碍，保持了学习热情并顺利结课。\n\ncoursera-deep-learning 的核心价值在于为自学者提供了一套权威的“纠错地图”，让学习者在独立探索与获得关键指引之间找到最佳平衡点。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FHeroKillerEver_coursera-deep-learning_7f5c2873.png","HeroKillerEver","Haibin YU","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FHeroKillerEver_ec5e29d2.jpg","Surviving","TikTok","Singapore","buaanusyu@gmail.com",null,"herokillerever.github.io","https:\u002F\u002Fgithub.com\u002FHeroKillerEver",[88,92],{"name":89,"color":90,"percentage":91},"Jupyter Notebook","#DA5B0B",98.9,{"name":93,"color":94,"percentage":95},"Python","#3572A5",1.1,644,619,"2026-03-15T06:36:32","","未说明",{"notes":102,"python":100,"dependencies":103},"该仓库仅为 Coursera 深度学习专项课程（由 Andrew Ng 教授主讲）的测验答案和编程作业参考代码，并非独立运行的软件工具。README 中未包含任何关于操作系统、硬件配置、Python 版本或依赖库的具体安装要求。用户需自行参照原课程环境进行配置，通常涉及基础的 Python 数据科学栈（如 NumPy, Matplotlib）及 TensorFlow（课程后期章节提及）。",[],[18],"2026-03-27T02:49:30.150509","2026-04-13T23:54:47.700681",[],[]]