[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-amanchadha--coursera-deep-learning-specialization":3,"tool-amanchadha--coursera-deep-learning-specialization":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":70,"readme_en":71,"readme_zh":72,"quickstart_zh":73,"use_case_zh":74,"hero_image_url":75,"owner_login":76,"owner_name":77,"owner_avatar_url":78,"owner_bio":79,"owner_company":80,"owner_location":81,"owner_email":82,"owner_twitter":83,"owner_website":84,"owner_url":85,"languages":86,"stars":103,"forks":104,"last_commit_at":105,"license":83,"difficulty_score":23,"env_os":106,"env_gpu":106,"env_ram":106,"env_deps":107,"category_tags":116,"github_topics":117,"view_count":23,"oss_zip_url":83,"oss_zip_packed_at":83,"status":16,"created_at":138,"updated_at":139,"faqs":140,"releases":171},3307,"amanchadha\u002Fcoursera-deep-learning-specialization","coursera-deep-learning-specialization","Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai: (i) Neural Networks and Deep Learning; (ii) Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization; (iii) Structuring Machine Learning Projects; (iv) Convolutional Neural Networks; (v) Sequence Models","coursera-deep-learning-specialization 是一个汇聚了吴恩达（Andrew Ng）在 Coursera 上开设的深度学习专项课程全部精华内容的开源资源库。它完整收录了从神经网络基础、超参数调优、机器学习项目构建，到卷积神经网络和序列模型等五门核心课程的编程作业、测验题及详细笔记。\n\n对于许多自学者而言，深度学习课程中的代码环境配置复杂，且课后练习缺乏系统的参考答案与思路梳理，这往往是学习路上的拦路虎。coursera-deep-learning-specialization 有效解决了这一痛点，它不仅提供了基于最新 TensorFlow 2 框架更新的代码实现，还通过预置脚本一键下载所需数据集和预训练模型，极大降低了环境搭建门槛。此外，仓库中包含了逐步构建深度神经网络的实战案例，帮助学习者直观理解算法原理。\n\n这套资源特别适合希望系统掌握深度学习技术的开发者、人工智能领域的研究人员以及计算机相关专业的学生使用。无论是想要夯实理论基础，还是准备技术面试，用户都能从中找到高质量的实战素材。其独特的亮点在于紧跟技术迭代，及时将旧版 TensorFlow 1 ","coursera-deep-learning-specialization 是一个汇聚了吴恩达（Andrew Ng）在 Coursera 上开设的深度学习专项课程全部精华内容的开源资源库。它完整收录了从神经网络基础、超参数调优、机器学习项目构建，到卷积神经网络和序列模型等五门核心课程的编程作业、测验题及详细笔记。\n\n对于许多自学者而言，深度学习课程中的代码环境配置复杂，且课后练习缺乏系统的参考答案与思路梳理，这往往是学习路上的拦路虎。coursera-deep-learning-specialization 有效解决了这一痛点，它不仅提供了基于最新 TensorFlow 2 框架更新的代码实现，还通过预置脚本一键下载所需数据集和预训练模型，极大降低了环境搭建门槛。此外，仓库中包含了逐步构建深度神经网络的实战案例，帮助学习者直观理解算法原理。\n\n这套资源特别适合希望系统掌握深度学习技术的开发者、人工智能领域的研究人员以及计算机相关专业的学生使用。无论是想要夯实理论基础，还是准备技术面试，用户都能从中找到高质量的实战素材。其独特的亮点在于紧跟技术迭代，及时将旧版 TensorFlow 1 代码迁移至更现代的 TensorFlow 2 版本，确保所学内容与当前工业界标准同步，是入门并精通深度学习不可多得的实用指南。","# Deep Learning Specialization on Coursera (offered by deeplearning.ai)\n\nProgramming assignments and quizzes from all courses in the Coursera [Deep Learning specialization](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning) offered by `deeplearning.ai`.\n\nInstructor: [Andrew Ng](http:\u002F\u002Fwww.andrewng.org\u002F)\n\n## Notes\n\n### For detailed interview-ready notes on all courses in the Coursera Deep Learning specialization, refer [www.aman.ai](https:\u002F\u002Faman.ai\u002F).\n\n## Setup\n\nRun ```setup.sh``` to (i) download a pre-trained VGG-19 dataset and (ii) extract the zip'd pre-trained models and datasets that are needed for all the assignments.\n\n## Credits\n\nThis repo contains my work for this specialization. The code base, quiz questions and diagrams are taken from the [Deep Learning Specialization on Coursera](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning), unless specified otherwise.\n\n## 2021 Version\n\nThis specialization was updated in April 2021 to include developments in deep learning and programming frameworks, with the biggest change being shifting from TensorFlow 1 to TensorFlow 2. This repo has been updated accordingly as well.\n\n## Programming Assignments\n\n### Course 1: Neural Networks and Deep Learning\n\n  - [Week 2 - PA 1 - Python Basics with Numpy](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%202\u002FPython%20Basics%20with%20Numpy\u002FPython_Basics_With_Numpy_v3a.ipynb)\n  - [Week 2 - PA 2 - Logistic Regression with a Neural Network mindset](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%202\u002FLogistic%20Regression%20as%20a%20Neural%20Network\u002FLogistic_Regression_with_a_Neural_Network_mindset_v6a.ipynb)\n  - [Week 3 - PA 3 - Planar data classification with one hidden layer](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%203\u002FPlanar%20data%20classification%20with%20one%20hidden%20layer\u002FPlanar_data_classification_with_onehidden_layer_v6c.ipynb)\n  - [Week 4 - PA 4 - Building your Deep Neural Network: Step by Step](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%204\u002FBuilding%20your%20Deep%20Neural%20Network%20-%20Step%20by%20Step\u002FBuilding_your_Deep_Neural_Network_Step_by_Step_v8a.ipynb)\n  - [Week 4 - PA 5 - Deep Neural Network for Image Classification: Application](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%204\u002FDeep%20Neural%20Network%20Application_%20Image%20Classification\u002FDeep%20Neural%20Network%20-%20Application%20v8.ipynb)\n\n### Course 2: Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization\n\n  - [Week 1 - PA 1 - Initialization](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%201\u002FInitialization\u002FInitialization.ipynb)\n  - [Week 1 - PA 2 - Regularization](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%201\u002FRegularization\u002FRegularization_v2a.ipynb)\n  - [Week 1 - PA 3 - Gradient Checking](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%201\u002FGradient%20Checking\u002FGradient%20Checking%20v1.ipynb)\n  - [Week 2 - PA 4 - Optimization Methods](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%202\u002FOptimization_methods_v1b.ipynb)\n  - [Week 3 - PA 5 - TensorFlow Tutorial](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%203\u002FTensorflow_introduction.ipynb)\n\n### Course 3: Structuring Machine Learning Projects\n\n  - There are no programming assignments for this course. But this course comes with very interesting case study quizzes (below).\n  \n### Course 4: Convolutional Neural Networks\n\n  - [Week 1 - PA 1 - Convolutional Model: step by step](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%201\u002FConvolution_model_Step_by_Step_v1.ipynb)\n  - [Week 1 - PA 2 - Convolutional Neural Networks: Application](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%201\u002FConvolution_model_Application.ipynb)\n  - [Week 2 - PA 1 - Keras - Tutorial - Happy House](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%202\u002FKerasTutorial\u002FKeras%20-%20Tutorial%20-%20Happy%20House%20v2.ipynb)\n  - [Week 2 - PA 2 - Residual Networks](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%202\u002FResNets\u002FResidual_Networks.ipynb)\n  - [Week 2 - PA 2 - Transfer Learning with MobileNet](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%202\u002FTransfer%20Learning%20with%20MobileNet\u002FTransfer_learning_with_MobileNet_v1.ipynb)\n  - [Week 3 - PA 1 - Car detection with YOLO for Autonomous Driving](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%203\u002FCar%20detection%20for%20Autonomous%20Driving\u002FAutonomous_driving_application_Car_detection.ipynb)\n  - [Week 3 - PA 2 - Image Segmentation Unet](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%203\u002FImage%20Segmentation%20Unet\u002FImage_segmentation_Unet_v2.ipynb)\n  - [Week 4 - PA 1 - Art Generation with Neural Style Transfer](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%204\u002FNeural%20Style%20Transfer\u002FArt_Generation_with_Neural_Style_Transfer.ipynb)    \n  - [Week 4 - PA 2 - Face Recognition](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%204\u002FFace%20Recognition\u002FFace_Recognition.ipynb)\n  \n### Course 5: Sequence Models\n\n  - [Week 1 - PA 1 - Building a Recurrent Neural Network - Step by Step](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%201\u002FBuilding%20a%20Recurrent%20Neural%20Network%20-%20Step%20by%20Step\u002FBuilding_a_Recurrent_Neural_Network_Step_by_Step.ipynb)\n  - [Week 1 - PA 2 - Dinosaur Land -- Character-level Language Modeling](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%201\u002FDinosaur%20Island%20--%20Character-level%20language%20model\u002FDinosaurus_Island_Character_level_language_model.ipynb)\n  - [Week 1 - PA 3 - Jazz improvisation with LSTM](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%201\u002FJazz%20improvisation%20with%20LSTM\u002FImprovise_a_Jazz_Solo_with_an_LSTM_Network_v4_Solution.ipynb)  \n  - [Week 2 - PA 1 - Word Vector Representation and Debiasing](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%202\u002FWord%20Vector%20Representation\u002FOperations_on_word_vectors_v2a.ipynb)  \n  - [Week 2 - PA 2 - Emojify!](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%202\u002FEmojify\u002FEmoji_v3a.ipynb)  \n  - [Week 3 - PA 1 - Neural Machine Translation with Attention](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%203\u002FMachine%20Translation\u002FNeural_machine_translation_with_attention_v4a.ipynb)  \n  - [Week 3 - PA 2 - Trigger Word Detection](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%203\u002FTrigger%20word%20detection\u002FTrigger_word_detection_v2a.ipynb)\n  - [Week 4 - PA 1 - Transformer Network](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%204\u002FTransformer%20Subclass\u002FC5_W4_A1_Transformer_Subclass_v1.ipynb)  \n  - [Week 3 - PA 2 - Transformer Network Application: Named-Entity Recognition](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%203\u002FNamed%20Entity%20Recognition\u002FTransformer_application_Named_Entity_Recognition.ipynb)   \n  - [Week 3 - PA 2 - Transformer Network Application: Question Answering](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%203\u002FQuestion%20Answering\u002FQA_transformer.ipynb) \n  \n## Quiz Solutions\n\n### Course 1: Neural Networks and Deep Learning\n\n  - Week 1 Quiz - Introduction to deep learning: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%201\u002FWeek%201%20Quiz%20-%20Introduction%20to%20deep%20learning.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%201\u002FWeek%201%20Quiz%20-%20Introduction%20to%20deep%20learning.pdf)\n  - Week 2 Quiz - Neural Network Basics: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Neural%20Network%20Basics.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Neural%20Network%20Basics.pdf)\n  - Week 3 Quiz - Shallow Neural Networks: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Shallow%20Neural%20Networks.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Shallow%20Neural%20Networks.pdf)\n  - Week 4 Quiz - Key concepts on Deep Neural Networks: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%204\u002FWeek%204%20Quiz%20-%20Key%20concepts%20on%20Deep%20Neural%20Networks.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%204\u002FWeek%204%20Quiz%20-%20Key%20concepts%20on%20Deep%20Neural%20Networks.pdf)\n\n### Course 2: Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization\n\n  - Week 1 Quiz - Practical aspects of deep learning: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%201\u002FWeek%201%20Quiz%20-%20Practical%20aspects%20of%20deep%20learning.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%201\u002FWeek%201%20Quiz%20-%20Practical%20aspects%20of%20deep%20learning.pdf)\n  - Week 2 Quiz - Optimization algorithms: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Optimization%20algorithms.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Optimization%20algorithms.pdf)\n  - Week 3 Quiz - Hyperparameter tuning, Batch Normalization, Programming Frameworks: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Hyperparameter%20tuning%2C%20Batch%20Normalization%2C%20Programming%20Frameworks.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Hyperparameter%20tuning%2C%20Batch%20Normalization%2C%20Programming%20Frameworks.pdf)\n  \n### Course 3: Structuring Machine Learning Projects\n\n  - Week 1 Quiz - Bird recognition in the city of Peacetopia (case study): [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC3%20-%20Structuring%20Machine%20Learning%20Projects\u002FWeek%201%20Quiz%20-%20Bird%20recognition%20in%20the%20city%20of%20Peacetopia%20(case%20study).md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC3%20-%20Structuring%20Machine%20Learning%20Projects\u002FWeek%201%20Quiz%20-%20Bird%20recognition%20in%20the%20city%20of%20Peacetopia%20(case%20study).pdf)\n  - Week 2 Quiz - Autonomous driving (case study): [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC3%20-%20Structuring%20Machine%20Learning%20Projects\u002FWeek%202%20Quiz%20-%20Autonomous%20driving%20(case%20study).md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC3%20-%20Structuring%20Machine%20Learning%20Projects\u002FWeek%202%20Quiz%20-%20Autonomous%20driving%20(case%20study).pdf)\n\n### Course 4: Convolutional Neural Networks\n\n  - Week 1 Quiz - The basics of ConvNets: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%201\u002FWeek%201%20Quiz%20-%20The%20basics%20of%20ConvNets.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%201\u002FWeek%201%20Quiz%20-%20The%20basics%20of%20ConvNets.pdf)\n  - Week 2 Quiz - Deep convolutional models: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Deep%20convolutional%20models.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Deep%20convolutional%20models.pdf)\n  - Week 3 Quiz - Detection algorithms: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Detection%20algorithms.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Detection%20algorithms.pdf)\n  - Week 4 Quiz - Special applications: Face recognition & Neural style transfer: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%204\u002FWeek%204%20Quiz%20-%20Special%20applications%20Face%20Recognition%20and%20Neural%20Style%20Transfer.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%204\u002FWeek%204%20Quiz%20-%20Special%20applications%20Face%20Recognition%20and%20Neural%20Style%20Transfer.pdf)\n\n### Course 5: Sequence Models\n\n  - Week 1 Quiz - Recurrent Neural Networks: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%201\u002FWeek%201%20Quiz%20-%20Recurrent%20Neural%20Networks.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%201\u002FWeek%201%20Quiz%20-%20Recurrent%20Neural%20Networks.pdf)\n  - Week 2 Quiz - Natural Language Processing & Word Embeddings: [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Natural%20Language%20Processing%20%26%20Word%20Embeddings.pdf)\n  - Week 3 Quiz - Sequence models & Attention mechanism: [Text](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Sequence%20models%20%26%20Attention%20mechanisms.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Sequence%20models%20%26%20Attention%20mechanisms.pdf)\n\n## Disclaimer\n\nI recognize the time people spend on building intuition, understanding new concepts and debugging assignments. The solutions uploaded here are **only for reference**. They are meant to unblock you if you get stuck somewhere. Please do not copy any part of the code as-is (the programming assignments are fairly easy if you read the instructions carefully). Similarly, try out the quizzes yourself before you refer to the quiz solutions. This course is the most straight-forward deep learning course I have ever taken, with fabulous course content and structure. It's a treasure by the deeplearning.ai team.\n","# Coursera 上的深度学习专项课程（由 deeplearning.ai 提供）\n\n来自 Coursera [深度学习专项课程](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning) 中所有课程的编程作业和测验，该专项课程由 `deeplearning.ai` 提供。\n\n讲师：[Andrew Ng](http:\u002F\u002Fwww.andrewng.org\u002F)\n\n## 笔记\n\n### 如需深度学习专项课程各门课程的详细面试备考笔记，请访问 [www.aman.ai](https:\u002F\u002Faman.ai\u002F)。\n\n## 设置\n\n运行 ```setup.sh``` 脚本，以 (i) 下载预训练的 VGG-19 数据集，以及 (ii) 解压所有作业所需的已压缩的预训练模型和数据集。\n\n## 致谢\n\n此仓库包含我在该专项课程中的作业。代码库、测验题目和图表均来自 Coursera 上的 [深度学习专项课程](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning)，除非另有说明。\n\n## 2021 版本\n\n该专项课程于 2021 年 4 月更新，纳入了深度学习和编程框架的最新进展，其中最大的变化是从 TensorFlow 1 迁移到 TensorFlow 2。本仓库也相应地进行了更新。\n\n## 编程作业\n\n### 第 1 课：神经网络与深度学习\n\n  - [第 2 周 - 作业 1 - 使用 NumPy 的 Python 基础](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%202\u002FPython%20Basics%20with%20Numpy\u002FPython_Basics_With_Numpy_v3a.ipynb)\n  - [第 2 周 - 作业 2 - 以神经网络思维实现逻辑回归](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%202\u002FLogistic%20Regression%20as%20a%20Neural%20Network\u002FLogistic_Regression_with_a_Neural_Network_mindset_v6a.ipynb)\n  - [第 3 周 - 作业 3 - 具有一个隐藏层的平面数据分类](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%203\u002FPlanar%20data%20classification%20with%20one%20hidden%20layer\u002FPlanar_data_classification_with_onehidden_layer_v6c.ipynb)\n  - [第 4 周 - 作业 4 - 手把手构建深度神经网络](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%204\u002FBuilding%20your%20Deep%20Neural%20Network%20-%20Step%20by%20Step\u002FBuilding_your_Deep_Neural_Network_Step_by_Step_v8a.ipynb)\n  - [第 4 周 - 作业 5 - 用于图像分类的深度神经网络：应用](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%204\u002FDeep%20Neural%20Network%20Application_%20Image%20Classification\u002FDeep%20Neural%20Network%20-%20Application%20v8.ipynb)\n\n### 第 2 课：改进深度神经网络：超参数调优、正则化与优化\n\n  - [第 1 周 - 作业 1 - 参数初始化](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%201\u002FInitialization\u002FInitialization.ipynb)\n  - [第 1 周 - 作业 2 - 正则化](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%201\u002FRegularization\u002FRegularization_v2a.ipynb)\n  - [第 1 周 - 作业 3 - 梯度检查](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%201\u002FGradient%20Checking\u002FGradient%20Checking%20v1.ipynb)\n  - [第 2 周 - 作业 4 - 优化方法](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%202\u002FOptimization_methods_v1b.ipynb)\n  - [第 3 周 - 作业 5 - TensorFlow 教程](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%203\u002FTensorflow_introduction.ipynb)\n\n### 第 3 课：机器学习项目结构设计\n\n  - 本课程没有编程作业。但本课程附带非常有趣的案例研究测验（见下文）。\n\n### 课程4：卷积神经网络\n\n  - [第1周 - 实践作业1 - 卷积模型：逐步实现](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%201\u002FConvolution_model_Step_by_Step_v1.ipynb)\n  - [第1周 - 实践作业2 - 卷积神经网络：应用](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%201\u002FConvolution_model_Application.ipynb)\n  - [第2周 - 实践作业1 - Keras教程：快乐之家](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%202\u002FKerasTutorial\u002FKeras%20-%20Tutorial%20-%20Happy%20House%20v2.ipynb)\n  - [第2周 - 实践作业2 - 残差网络](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%202\u002FResNets\u002FResidual_Networks.ipynb)\n  - [第2周 - 实践作业2 - 使用MobileNet的迁移学习](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%202\u002FTransfer%20Learning%20with%20MobileNet\u002FTransfer_learning_with_MobileNet_v1.ipynb)\n  - [第3周 - 实践作业1 - 自动驾驶中的YOLO车辆检测](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%203\u002FCar%20detection%20for%20Autonomous%20Driving\u002FAutonomous_driving_application_Car_detection.ipynb)\n  - [第3周 - 实践作业2 - 图像分割Unet](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%203\u002FImage%20Segmentation%20Unet\u002FImage_segmentation_Unet_v2.ipynb)\n  - [第4周 - 实践作业1 - 使用神经风格迁移生成艺术作品](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%204\u002FNeural%20Style%20Transfer\u002FArt_Generation_with_Neural_Style_Transfer.ipynb)    \n  - [第4周 - 实践作业2 - 人脸识别](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%204\u002FFace%20Recognition\u002FFace_Recognition.ipynb)\n  \n### 课程5：序列模型\n\n  - [第1周 - 实践作业1 - 构建循环神经网络：逐步实现](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%201\u002FBuilding%20a%20Recurrent%20Neural%20Network%20-%20Step%20by%20Step\u002FBuilding_a_Recurrent_Neural_Network_Step_by_Step.ipynb)\n  - [第1周 - 实践作业2 - 恐龙岛——字符级语言建模](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%201\u002FDinosaur%20Island%20--%20Character-level%20language%20model\u002FDinosaurus_Island_Character_level_language_model.ipynb)\n  - [第1周 - 实践作业3 - 使用LSTM即兴演奏爵士乐](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%201\u002FJazz%20improvisation%20with%20LSTM\u002FImprovise_a_Jazz_Solo_with_an_LSTM_Network_v4_Solution.ipynb)  \n  - [第2周 - 实践作业1 - 词向量表示与去偏处理](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%202\u002FWord%20Vector%20Representation\u002FOperations_on_word_vectors_v2a.ipynb)  \n  - [第2周 - 实践作业2 - 表情符号化！](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%202\u002FEmojify\u002FEmoji_v3a.ipynb)  \n  - [第3周 - 实践作业1 - 带注意力机制的神经机器翻译](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%203\u002FMachine%20Translation\u002FNeural_machine_translation_with_attention_v4a.ipynb)  \n  - [第3周 - 实践作业2 - 触发词检测](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%203\u002FTrigger%20word%20detection\u002FTrigger_word_detection_v2a.ipynb)\n  - [第4周 - 实践作业1 - Transformer网络](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%204\u002FTransformer%20Subclass\u002FC5_W4_A1_Transformer_Subclass_v1.ipynb)  \n  - [第3周 - 实践作业2 - Transformer网络的应用：命名实体识别](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%203\u002FNamed%20Entity%20Recognition\u002FTransformer_application_Named_Entity_Recognition.ipynb)   \n  - [第3周 - 实践作业2 - Transformer网络的应用：问答系统](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%203\u002FQuestion%20Answering\u002FQA_transformer.ipynb) \n  \n## 测验答案\n\n### 课程1：神经网络与深度学习\n\n  - 第1周测验——深度学习导论：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%201\u002FWeek%201%20Quiz%20-%20Introduction%20to%20deep%20learning.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%201\u002FWeek%201%20Quiz%20-%20Introduction%20to%20deep%20learning.pdf)\n  - 第2周测验——神经网络基础：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Neural%20Network%20Basics.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Neural%20Network%20Basics.pdf)\n  - 第3周测验——浅层神经网络：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Shallow%20Neural%20Networks.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Shallow%20Neural%20Networks.pdf)\n  - 第4周测验——深度神经网络的关键概念：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%204\u002FWeek%204%20Quiz%20-%20Key%20concepts%20on%20Deep%20Neural%20Networks.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC1%20-%20Neural%20Networks%20and%20Deep%20Learning\u002FWeek%204\u002FWeek%204%20Quiz%20-%20Key%20concepts%20on%20Deep%20Neural%20Networks.pdf)\n\n### 课程2：改进深度神经网络：超参数调优、正则化与优化\n\n  - 第1周测验——深度学习的实践方面：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%201\u002FWeek%201%20Quiz%20-%20Practical%20aspects%20of%20deep%20learning.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%201\u002FWeek%201%20Quiz%20-%20Practical%20aspects%20of%20deep%20learning.pdf)\n  - 第2周测验——优化算法：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Optimization%20algorithms.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Optimization%20algorithms.pdf)\n  - 第3周测验——超参数调优、批归一化、编程框架：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Hyperparameter%20tuning%2C%20Batch%20Normalization%2C%20Programming%20Frameworks.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC2%20-%20Improving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Hyperparameter%20tuning%2C%20Batch%20Normalization%2C%20Programming%20Frameworks.pdf)\n  \n### 课程3：机器学习项目结构设计\n\n  - 第1周测验——和平城的鸟类识别（案例研究）：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC3%20-%20Structuring%20Machine%20Learning%20Projects\u002FWeek%201%20Quiz%20-%20Bird%20recognition%20in%20the%20city%20of%20Peacetopia%20(case%20study).md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC3%20-%20Structuring%20Machine%20Learning%20Projects\u002FWeek%201%20Quiz%20-%20Bird%20recognition%20in%20the%20city%20of%20Peacetopia%20(case%20study).pdf)\n  - 第2周测验——自动驾驶（案例研究）：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC3%20-%20Structuring%20Machine%20Learning%20Projects\u002FWeek%202%20Quiz%20-%20Autonomous%20driving%20(case%20study).md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC3%20-%20Structuring%20Machine%20Learning%20Projects\u002FWeek%202%20Quiz%20-%20Autonomous%20driving%20(case%20study).pdf)\n\n### 课程4：卷积神经网络\n\n  - 第1周测验——卷积神经网络基础：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%201\u002FWeek%201%20Quiz%20-%20The%20basics%20of%20ConvNets.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%201\u002FWeek%201%20Quiz%20-%20The%20basics%20of%20ConvNets.pdf)\n  - 第2周测验——深度卷积模型：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Deep%20convolutional%20models.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Deep%20convolutional%20models.pdf)\n  - 第3周测验——目标检测算法：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Detection%20algorithms.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Detection%20algorithms.pdf)\n  - 第4周测验——特殊应用：人脸识别与神经风格迁移：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%204\u002FWeek%204%20Quiz%20-%20Special%20applications%20Face%20Recognition%20and%20Neural%20Style%20Transfer.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC4%20-%20Convolutional%20Neural%20Networks\u002FWeek%204\u002FWeek%204%20Quiz%20-%20Special%20applications%20Face%20Recognition%20and%20Neural%20Style%20Transfer.pdf)\n\n### 课程5：序列模型\n\n  - 第1周测验——循环神经网络：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%201\u002FWeek%201%20Quiz%20-%20Recurrent%20Neural%20Networks.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%201\u002FWeek%201%20Quiz%20-%20Recurrent%20Neural%20Networks.pdf)\n  - 第2周测验——自然语言处理与词嵌入：[PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%202\u002FWeek%202%20Quiz%20-%20Natural%20Language%20Processing%20%26%20Word%20Embeddings.pdf)\n  - 第3周测验——序列模型与注意力机制：[文本](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Sequence%20models%20%26%20Attention%20mechanisms.md) | [PDF](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fblob\u002Fmaster\u002FC5%20-%20Sequence%20Models\u002FWeek%203\u002FWeek%203%20Quiz%20-%20Sequence%20models%20%26%20Attention%20mechanisms.pdf)\n\n## 免责声明\n\n我深知大家在培养直觉、理解新概念以及调试作业上所花费的时间。这里上传的解答**仅供参考**，旨在帮助你在遇到困难时继续前进。请勿照搬任何代码（只要仔细阅读说明，编程作业其实并不难）。同样地，在参考测验答案之前，请先自行尝试完成测验。这门课程是我迄今为止学习过的最直观的深度学习课程，其内容和结构都非常出色，堪称deeplearning.ai团队的瑰宝。","# Coursera 深度学习专项课程开源项目快速上手指南\n\n本项目收录了由吴恩达（Andrew Ng）主讲、deeplearning.ai 提供的 Coursera [深度学习专项课程](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning) 中的所有编程作业（Programming Assignments）和测验题解。代码库已更新至 2021 版本，全面支持 **TensorFlow 2**。\n\n## 环境准备\n\n在开始之前，请确保您的开发环境满足以下要求：\n\n*   **操作系统**：Linux, macOS 或 Windows (推荐 WSL2)\n*   **Python 版本**：Python 3.6+ (推荐 3.8 或 3.9)\n*   **核心依赖**：\n    *   NumPy\n    *   Matplotlib\n    *   TensorFlow 2.x\n    *   Jupyter Notebook \u002F JupyterLab\n*   **网络环境**：由于部分脚本需要下载预训练模型（如 VGG-19），建议确保网络连接畅通。如遇下载缓慢，可尝试配置国内镜像源或使用代理。\n\n## 安装步骤\n\n### 1. 克隆项目仓库\n首先将代码库克隆到本地：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Famanchadha\u002Fcoursera-deep-learning-specialization.git\ncd coursera-deep-learning-specialization\n```\n\n### 2. 安装 Python 依赖\n建议使用虚拟环境（如 `venv` 或 `conda`）来管理依赖。创建并激活环境后，安装所需包：\n\n```bash\n# 如果使用 pip\npip install -r requirements.txt\n\n# 如果项目中未提供 requirements.txt，请手动安装核心库\npip install numpy matplotlib tensorflow jupyter notebook\n```\n\n> **提示**：国内用户可使用清华或阿里镜像源加速安装：\n> `pip install -r requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple`\n\n### 3. 下载数据集与预训练模型\n项目包含一个自动化脚本，用于下载作业所需的预训练 VGG-19 数据集并解压相关文件。在项目根目录下运行：\n\n```bash\nchmod +x setup.sh\n.\u002Fsetup.sh\n```\n\n*注：Windows 用户若无法直接运行 `.sh` 文件，可手动查看 `setup.sh` 内容，下载对应的 zip 文件并解压至指定目录，或直接运行对应的 Jupyter Notebook 单元格进行下载。*\n\n## 基本使用\n\n本项目主要通过 **Jupyter Notebook** 进行交互式学习。每个课程章节都对应具体的 `.ipynb` 文件。\n\n### 启动 Jupyter Notebook\n在项目根目录下运行以下命令启动服务：\n\n```bash\njupyter notebook\n```\n\n浏览器将自动打开并显示文件目录。\n\n### 运行编程作业\n根据您正在学习的课程，进入对应的文件夹并打开 Notebook。例如，要开始 **课程 1：神经网络与深度学习** 的第二个作业（逻辑回归），请按以下路径操作：\n\n1.  进入目录：`C1 - Neural Networks and Deep Learning\u002FWeek 2\u002FLogistic Regression as a Neural Network\u002F`\n2.  打开文件：`Logistic_Regression_with_a_Neural_Network_mindset_v6a.ipynb`\n3.  点击菜单栏的 **Cell** -> **Run All** 依次执行代码单元格，或按 `Shift + Enter` 逐个运行。\n\n### 查看测验解析\n每个课程的周测验答案以 `.md` (文本) 和 `.pdf` 格式提供。您可以直接在 GitHub 仓库的 `nbviewer` 链接中预览，或在本地使用 Markdown 阅读器打开 `Week X Quiz` 相关文件进行核对。\n\n### 学习路径建议\n*   **Course 1**: 从 Python 基础与 Numpy 开始，逐步构建深层神经网络。\n*   **Course 2**: 重点实践超参数调优、正则化及优化算法（如 Adam）。\n*   **Course 3**: 无编程作业，侧重机器学习项目架构的案例研究。\n*   **Course 4**: 深入卷积神经网络（CNN），实践图像分类、目标检测（YOLO）及风格迁移。\n*   **Course 5**: 探索序列模型，包括 RNN、LSTM、Transformer 及自然语言处理应用。","一名刚转行深度学习的数据分析师，正试图从零构建图像分类模型以应对公司新项目，却因理论基础薄弱而陷入困境。\n\n### 没有 coursera-deep-learning-specialization 时\n- **理论碎片化**：在网上零散搜索“神经网络”或“正则化”概念，缺乏像吴恩达课程那样从逻辑回归到深层网络的系统性知识串联。\n- **代码实现难**：面对反向传播等核心算法，只能复制粘贴黑盒代码，一旦报错便无法理解底层的梯度计算与矩阵维度变换。\n- **调优无头绪**：模型训练效果不佳时，不知道是超参数设置问题还是过拟合导致，缺乏系统的调试方法论（如梯度检查、优化器选择）。\n- **环境配置坑**：在 TensorFlow 1 与 2 的版本差异中浪费大量时间，找不到适配最新框架的练习代码和数据集。\n\n### 使用 coursera-deep-learning-specialization 后\n- **知识体系化**：通过五门课程的笔记与测验，建立起从基础神经网络到卷积、序列模型的完整认知地图，面试准备也更有底气。\n- **手写核心算法**：借助\"Step by Step\"编程作业，亲手用 Numpy 实现深层网络前向与反向传播，彻底吃透了数据流动的本质。\n- **掌握调优策略**：利用超参数调整、正则化及优化方法的专项练习，能快速定位模型瓶颈并显著提升准确率。\n- **开箱即用资源**：运行 `setup.sh` 即可自动获取预训练的 VGG-19 数据集和适配 TensorFlow 2 的代码，立即投入实战演练。\n\ncoursera-deep-learning-specialization 将抽象的深度学习理论转化为可执行的代码实践，帮助学习者跨越了从“看懂文章”到“写出模型”的关键鸿沟。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Famanchadha_coursera-deep-learning-specialization_1edc1022.png","amanchadha","Aman Chadha","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Famanchadha_bc853c08.jpg","GenAI @ AWS • Ex: Apple, Stanford","Amazon Inc. \u002F Ex- \u002F Stanford University","San Francisco Bay Area, CA","aman@amanchadha.com",null,"www.aman.ai","https:\u002F\u002Fgithub.com\u002Famanchadha",[87,91,95,99],{"name":88,"color":89,"percentage":90},"Jupyter Notebook","#DA5B0B",98.7,{"name":92,"color":93,"percentage":94},"Python","#3572A5",0.8,{"name":96,"color":97,"percentage":98},"Roff","#ecdebe",0.5,{"name":100,"color":101,"percentage":102},"Shell","#89e051",0,4242,2645,"2026-04-04T01:29:24","未说明",{"notes":108,"python":106,"dependencies":109},"该项目为 Coursera 深度学习专项课程的编程作业合集。2021 年版本已从 TensorFlow 1 迁移至 TensorFlow 2。运行前需执行 setup.sh 脚本以下载预训练的 VGG-19 数据集并解压其他所需模型文件。课程涵盖神经网络基础、超参数调整、卷积神经网络（CNN）、序列模型及 Transformer 等内容。",[110,111,112,113,114,115],"numpy","tensorflow>=2.0","keras","jupyter","h5py","matplotlib",[26,13],[118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137],"deep-learning","coursera","coursera-assignment","coursera-specialization","coursera-machine-learning","andrew-ng","andrew-ng-course","convolutional-neural-networks","cnns","recurrent-neural-networks","rnns","convolutional-neural-network","recurrent-neural-network","hyperparameter-optimization","hyperparameter-tuning","neural-network","neural-networks","neural-machine-translation","neural-style-transfer","regularization","2026-03-27T02:49:30.150509","2026-04-06T08:52:27.310354",[141,146,151,156,161,166],{"id":142,"question_zh":143,"answer_zh":144,"source_url":145},15194,"打开数据集时出现 \"OSError: Unable to open file (file signature not found)\" 错误怎么办？","这是因为仓库中的许多文件（如数据集）使用了 Git LFS (Git Large File Storage)。如果在安装 git-lfs 之前克隆了仓库，下载的只是指向大文件的指针而非实际文件。\n\n解决方案：\n1. 确保已安装 git-lfs。安装步骤如下：\n   curl -s https:\u002F\u002Fpackagecloud.io\u002Finstall\u002Frepositories\u002Fgithub\u002Fgit-lfs\u002Fscript.deb.sh | sudo bash\n   sudo apt-get install git-lfs\n2. 如果之前已经克隆过仓库，请重新克隆：git clone \u003Crepo_path>\n3. 或者在现有仓库中运行 `git lfs pull` 来下载实际的 LFS 文件。\n完成上述步骤后，错误即可修复。","https:\u002F\u002Fgithub.com\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fissues\u002F4",{"id":147,"question_zh":148,"answer_zh":149,"source_url":150},15195,"如何运行 setup.sh 脚本？","需要先给脚本添加执行权限，然后运行它。请在终端中执行以下命令：\nchmod +x setup.sh\n.\u002Fsetup.sh\n\n如果仍然遇到问题，可能是因为相关的大文件（如数据集）未正确下载（参考 Git LFS 问题），或者脚本内部链接的资源需要手动下载。","https:\u002F\u002Fgithub.com\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fissues\u002F11",{"id":152,"question_zh":153,"answer_zh":154,"source_url":155},15196,"运行 setup.sh 时出现 \"End-of-central-directory signature not found\" 或 unzip 错误怎么办？","这通常是因为尝试解压的文件实际上是 Git LFS 的指针文件，而不是真正的压缩包。\n\n解决方法：\n1. 确保已安装 git-lfs：\n   curl -s https:\u002F\u002Fpackagecloud.io\u002Finstall\u002Frepositories\u002Fgithub\u002Fgit-lfs\u002Fscript.deb.sh | sudo bash\n   sudo apt-get install git-lfs\n2. 重新克隆仓库以获取真实文件：git clone \u003Crepo_path>\n3. 如果不想重新克隆，可以在当前目录运行 `git lfs pull` 下载所有大文件。\n完成后再次运行 setup.sh 即可正常解压。","https:\u002F\u002Fgithub.com\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fissues\u002F3",{"id":157,"question_zh":158,"answer_zh":159,"source_url":160},15197,"模型准确率很低（例如测试集只有 34%），且预测结果全为 0 或非预期值，可能的原因是什么？","这通常是因为训练集和测试集的展平（flatten）reshape 方式不正确，导致激活值异常。\n\n请尝试将数据 reshape 的代码修改为以下形式：\ntrain_set_x_flatten = train_set_x_orig.reshape(train_set_x_orig.shape[0], -1).T\ntest_set_x_flatten = test_set_x_orig.reshape(test_set_x_orig.shape[0], -1).T\n\n确保转置操作 (.T) 正确应用，使特征维度在行上，样本维度在列上（或反之，取决于具体网络实现要求，但通常需保持与课程代码一致）。","https:\u002F\u002Fgithub.com\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fissues\u002F5",{"id":162,"question_zh":163,"answer_zh":164,"source_url":165},15198,"无法下载特定的数据集文件（如 data.mat），GitHub 上的链接无效或打不开怎么办？","如果仓库中的链接失效或无法下载，可以尝试以下方法：\n1. 检查是否因未安装 Git LFS 导致下载的是空指针文件（见其他 FAQ）。\n2. 寻找其他镜像仓库。例如有用户在该问题的评论中提到，可以在以下地址找到相关文件：https:\u002F\u002Fgithub.com\u002Fcruzcid\u002FImproving-Deep-Neural-Networks---Hyperparameter-tuning-Regularization-and-Optimization\u002Ftree\u002Fmaster\u002FRegularization%20-%20Assignment%202\n3. 直接从 Coursera 课程页面下载原始作业文件。","https:\u002F\u002Fgithub.com\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fissues\u002F25",{"id":167,"question_zh":168,"answer_zh":169,"source_url":170},15199,"加载 \"Cat vs non-cat\" 数据集时报错 \"file signature not found\" 如何解决？","该问题同样是由 Git LFS 文件未正确下载引起的。仓库中的 .h5 或其他数据文件是大文件存储对象。\n\n解决步骤：\n1. 安装 git-lfs (如果尚未安装)：\n   curl -s https:\u002F\u002Fpackagecloud.io\u002Finstall\u002Frepositories\u002Fgithub\u002Fgit-lfs\u002Fscript.deb.sh | sudo bash\n   sudo apt-get install git-lfs\n2. 重新克隆仓库：git clone \u003Crepo_url>\n   或者在现有仓库中执行：git lfs pull\n3. 验证文件大小是否正常（指针文件通常很小，只有几十字节）。\n修复后再次运行加载代码即可。","https:\u002F\u002Fgithub.com\u002Famanchadha\u002Fcoursera-deep-learning-specialization\u002Fissues\u002F2",[]]