[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-sjchoi86--dl_tutorials":3,"tool-sjchoi86--dl_tutorials":61},[4,18,28,36,45,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":24,"last_commit_at":25,"category_tags":26,"status":17},9989,"n8n","n8n-io\u002Fn8n","n8n 是一款面向技术团队的公平代码（fair-code）工作流自动化平台，旨在让用户在享受低代码快速构建便利的同时，保留编写自定义代码的灵活性。它主要解决了传统自动化工具要么过于封闭难以扩展、要么完全依赖手写代码效率低下的痛点，帮助用户轻松连接 400 多种应用与服务，实现复杂业务流程的自动化。\n\nn8n 特别适合开发者、工程师以及具备一定技术背景的业务人员使用。其核心亮点在于“按需编码”：既可以通过直观的可视化界面拖拽节点搭建流程，也能随时插入 JavaScript 或 Python 代码、调用 npm 包来处理复杂逻辑。此外，n8n 原生集成了基于 LangChain 的 AI 能力，支持用户利用自有数据和模型构建智能体工作流。在部署方面，n8n 提供极高的自由度，支持完全自托管以保障数据隐私和控制权，也提供云端服务选项。凭借活跃的社区生态和数百个现成模板，n8n 让构建强大且可控的自动化系统变得简单高效。",184740,2,"2026-04-19T23:22:26",[16,14,13,15,27],"插件",{"id":29,"name":30,"github_repo":31,"description_zh":32,"stars":33,"difficulty_score":10,"last_commit_at":34,"category_tags":35,"status":17},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,"2026-04-05T11:01:52",[14,15,13],{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":24,"last_commit_at":42,"category_tags":43,"status":17},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",161147,"2026-04-19T23:31:47",[14,13,44],"语言模型",{"id":46,"name":47,"github_repo":48,"description_zh":49,"stars":50,"difficulty_score":24,"last_commit_at":51,"category_tags":52,"status":17},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。",109154,"2026-04-18T11:18:24",[14,15,13],{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":24,"last_commit_at":59,"category_tags":60,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[27,13,15,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":77,"owner_email":78,"owner_twitter":79,"owner_website":80,"owner_url":81,"languages":79,"stars":82,"forks":83,"last_commit_at":84,"license":85,"difficulty_score":86,"env_os":87,"env_gpu":88,"env_ram":88,"env_deps":89,"category_tags":93,"github_topics":79,"view_count":24,"oss_zip_url":79,"oss_zip_packed_at":79,"status":17,"created_at":94,"updated_at":95,"faqs":96,"releases":97},10000,"sjchoi86\u002Fdl_tutorials","dl_tutorials","Deep learning tutorials (2nd ed.)","dl_tutorials 是一套系统化的深度学习开源教程（第二版），旨在帮助学习者从零开始掌握深度学习的核心理论与实战技能。它通过四周的渐进式课程，解决了初学者面对庞大知识体系时难以入手、理论与实践脱节的痛点。内容涵盖从 Python 基础、MNIST 图像处理入门，到卷积神经网络（CNN）、循环神经网络（RNN）等进阶架构的深度解析。\n\n这套教程特别适合希望转行 AI 的开发者、计算机专业学生以及需要夯实基础的研究人员。其独特亮点在于“学以致用”的教学设计：不仅详细讲解了 AlexNet、GoogLeNet、AlphaGo 等经典模型原理，更提供了大量基于 TensorFlow 的代码实战环节。用户可以跟随指引亲手实现多层感知机、去噪自编码器、语义分割及目标检测（如 YOLO、Faster RNN）等前沿应用，甚至学习如何构建和训练自己的数据集。此外，教程还涵盖了正则化、优化方法及 TensorBoard 可视化等工程必备技能。无论你是想理解算法背后的数学逻辑，还是渴望动手构建真实的 AI 项目，dl_tutorials 都能提供清晰的路径和丰富的资源支持。","# Deep learning tutorials\n Deep learning tutorials (2nd ed.)\n\n## Week1 \n1. [Deep learning intro.](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-1b%20Deep%20learning%20intro.pptx)\n2. [Python basics](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-1c%20Python%20basic%20(basic_python).pptx)\n3. [Let's play with images & MNIST](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-1d%20MNIST%20(basic_mnist)%20and%20image%20processing%20(basic_imgprocess).pptx)\n4. [Terminologies](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-2a%20Terminologies.pptx)\n\n## Week2 - Do you know deep learning?\n1. [CNN and AlexNet](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-2b%20CNN%20and%20AlexNet.pptx)\n2. [TensorFlow basics](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-2c%20TensorFlow%20basic%20(basic_tensorflow).pptx)\n3. [Logistic regression](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-2d%20Logistic%20regression%20(logistic_regression_mnist).pptx)\n4. [GoogLeNet](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-1b%20GoogLeNet.pptx)\n5. [AlphaGo: MCTS+CNN](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-1c%20AlphaGo.pptx)\n6. [Let's implement MLP!](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-1d%20Multi-layer%20perceptron%20(mlp_mnist_simple).pptx)\n7. [Let's play with you OWN DATASET](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-1e%20Generate%20your%20own%20dataset%20(basic_gendataset).pptx)\n8. [Regularization methods](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-1f%20Regulaziation.pptx)\n9. [Optimization methods](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-2a%20Optimizaiton%20methods.pptx)\n10. [Restricted Boltzmann Machine](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-2b%20Restricted%20Boltzmann%20machine.pptx)\n11. [Let's implement denoising autoencoder](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-2c%20Denoising%20auto-encoder%20(dae_mnist).pptx)\n\n## Week3 - CNN basics\n1. [Semantic segmentation: FCN, DeconvNet, DeepLab with atrous conv](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-1b%20Semantic%20segmentation%20details%2BSOTA.pptx)\n2. [Let's implement a simple CNN](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-1c%20What%20is%20CNN%20(cnn_mnist_simple).pptx)\n3. [Let's implement a basic CNN](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-1d%20Powerful%20CNN%20(cnn_mnist_basic).pptx)\n4. [Let's implement semantic segmentation](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-1e%20Implementing%20semantic%20segmentation%20(semseg_basic).pptx) \n5. [Weakly supervised localization: Global average pooling](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-2a%20Weakly%20supervised%20learning.pptx)\n6. [Implement MLP and CNN on your OWN DATASET](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-2b%20Use%20your%20own%20dataset%20(basic_gendataset%2C%20lr%2C%20mlp%2C%20cnn).pptx)\n7. [Denoising deconvolutional neural network](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-2c%20Denoising%20deconvolutional%20network.pptx)\n\n## Week4 - CNN applications + RNN basics\n1. [Image detection (RCNN, SPPnet, FastRCNN, FasterRCNN)](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-1a%20Image%20detection%20(RCNN%2C%20SPPnet%2C%20FastRCNN%2C%20FasterRCNN).pptx)\n2. [Other detections (YOLO, AttentionNet)](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-1b%20Other%20dections%20(YOLO%2C%20AttentionNet).pptx)\n3. [Let's use TensorBoards](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-1c%20TensorBoard.pptx)\n4. [RNN from Colah's blog](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-2a%20RNN%20(colah%20blog).pptx)\n5. [Visual QnA: DPPnet + MCBP!](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-2b%20Visual%20QnA.pptx)\n6. [Super resolution](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-2c%20Super%20resolution.pptx)\n7. [Deep reinforcement learning](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-2d%20Deep%20reinforcement%20learning.pptx)\n\n## Week5 - RNN applications\n1. [RNN basic + handwriting generation](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek5-1a%20RNN%20%2B%20LSTM%20%2B%20Handwrting%20Gen.pptx)\n2. [Let's implement RNNs](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek5-1b%20Implementing%20RNN%20(rnn_mnist_simple).pptx)\n3. [Let's implement Word2vec](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek5-2a%20Word2Vec%20again.pptx)\n4. [Image captioning: Show and Tell + Show, attend and tell](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek5-2b%20Image%20Captioning.pptx)\n5. [char-rnn + how can we use Hangul?](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek5-2c%20Hangul-RNN.pptx)\n\n## Week6 - Deep learning is so FUN!\n1. [Residual network and some analysis](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek6-1a%20Residual%20Networks%20and%20Analysis.pptx)\n2. [Neural Style: Texture synsthesis+Inverting CNN](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek6-1b%20Neural%20Style.pptx)\n3. [Let's implement neural style](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek6-1c%20Neural%20Style%20Code.pptx)\n4. [Bayesian optimization](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek6-2a%20Bayesian%20Optimization.pptx)\n5. [Adversaral attack?](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek6-2b%20Adversarial%20Attack.pptx)\n6. [Generative adversarial network](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek6-2c%20Generative%20Adversarial%20Network.pptx)\n","# 深度学习教程\n深度学习教程（第2版）\n\n## 第1周\n1. [深度学习简介](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-1b%20Deep%20learning%20intro.pptx)\n2. [Python基础](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-1c%20Python%20basic%20(basic_python).pptx)\n3. [让我们玩转图像与MNIST数据集](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-1d%20MNIST%20(basic_mnist)%20and%20image%20processing%20(basic_imgprocess).pptx)\n4. [术语](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-2a%20Terminologies.pptx)\n\n## 第2周 - 你了解深度学习吗？\n1. [CNN与AlexNet](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-2b%20CNN%20and%20AlexNet.pptx)\n2. [TensorFlow基础](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-2c%20TensorFlow%20basic%20(basic_tensorflow).pptx)\n3. [逻辑回归](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek1-2d%20Logistic%20regression%20(logistic_regression_mnist).pptx)\n4. [GoogLeNet](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-1b%20GoogLeNet.pptx)\n5. [AlphaGo：MCTS+CNN](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-1c%20AlphaGo.pptx)\n6. [让我们实现多层感知机！](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-1d%20Multi-layer%20perceptron%20(mlp_mnist_simple).pptx)\n7. [让我们使用自己的数据集](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-1e%20Generate%20your%20own%20dataset%20(basic_gendataset).pptx)\n8. [正则化方法](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-1f%20Regulaziation.pptx)\n9. [优化方法](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-2a%20Optimizaiton%20methods.pptx)\n10. [受限玻尔兹曼机](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-2b%20Restricted%20Boltzmann%20machine.pptx)\n11. [让我们实现去噪自编码器](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek2-2c%20Denoising%20auto-encoder%20(dae_mnist).pptx)\n\n## 第3周 - CNN基础\n1. [语义分割：FCN、DeconvNet、带空洞卷积的DeepLab](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-1b%20Semantic%20segmentation%20details%2BSOTA.pptx)\n2. [让我们实现一个简单的CNN](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-1c%20What%20is%20CNN%20(cnn_mnist_simple).pptx)\n3. [让我们实现一个基础的CNN](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-1d%20Powerful%20CNN%20(cnn_mnist_basic).pptx)\n4. [让我们实现语义分割](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-1e%20Implementing%20semantic%20segmentation%20(semseg_basic).pptx) \n5. [弱监督定位：全局平均池化](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-2a%20Weakly%20supervised%20learning.pptx)\n6. [在你自己的数据集上实现MLP和CNN](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-2b%20Use%20your%20own%20dataset%20(basic_gendataset%2C%20lr%2C%20mlp%2C%20cnn).pptx)\n7. [去噪反卷积神经网络](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek3-2c%20Denoising%20deconvolutional%20network.pptx)\n\n## 第4周 - CNN应用 + RNN基础\n1. [图像检测（RCNN、SPPnet、FastRCNN、FasterRCNN）](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-1a%20Image%20detection%20(RCNN%2C%20SPPnet%2C%20FastRCNN%2C%20FasterRCNN).pptx)\n2. [其他检测方法（YOLO、AttentionNet）](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-1b%20Other%20dections%20(YOLO%2C%20AttentionNet).pptx)\n3. [让我们使用TensorBoard](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-1c%20TensorBoard.pptx)\n4. [Colah博客中的RNN](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-2a%20RNN%20(colah%20blog).pptx)\n5. [视觉问答：DPPnet + MCBP！](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-2b%20Visual%20QnA.pptx)\n6. [超分辨率](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-2c%20Super%20resolution.pptx)\n7. [深度强化学习](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek4-2d%20Deep%20reinforcement%20learning.pptx)\n\n## 第5周 - RNN应用\n1. [RNN基础 + 手写体生成](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek5-1a%20RNN%20%2B%20LSTM%20%2B%20Handwrting%20Gen.pptx)\n2. [让我们实现RNN](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek5-1b%20Implementing%20RNN%20(rnn_mnist_simple).pptx)\n3. [让我们实现Word2vec](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek5-2a%20Word2Vec%20again.pptx)\n4. [图像字幕生成：Show and Tell + Show, attend and tell](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek5-2b%20Image%20Captioning.pptx)\n5. [char-rnn + 我们如何使用韩文字母？](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek5-2c%20Hangul-RNN.pptx)\n\n## 第6周 - 深度学习真有趣！\n1. [残差网络及一些分析](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek6-1a%20Residual%20Networks%20and%20Analysis.pptx)\n2. [神经风格：纹理合成+CNN反演](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek6-1b%20Neural%20Style.pptx)\n3. [让我们实现神经风格](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek6-1c%20Neural%20Style%20Code.pptx)\n4. [贝叶斯优化](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek6-2a%20Bayesian%20Optimization.pptx)\n5. [对抗攻击？](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek6-2b%20Adversarial%20Attack.pptx)\n6. [生成对抗网络](https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials\u002Fblob\u002Fmaster\u002Fpresentations\u002FWeek6-2c%20Generative%20Adversarial%20Network.pptx)","# dl_tutorials 快速上手指南\n\n`dl_tutorials` 是一套系统的深度学习教程（第二版），涵盖从 Python 基础、TensorFlow 入门到 CNN、RNN、GAN 等前沿架构的理论与实战代码。本指南将帮助你快速搭建环境并开始学习。\n\n## 环境准备\n\n在开始之前，请确保你的开发环境满足以下要求：\n\n*   **操作系统**：Windows, macOS 或 Linux (推荐 Ubuntu 18.04+)\n*   **Python 版本**：Python 3.6 - 3.8 (教程基于较早期的 TensorFlow 版本，过高版本可能存在兼容性差异)\n*   **核心依赖**：\n    *   TensorFlow (CPU 或 GPU 版本)\n    *   NumPy\n    *   Matplotlib\n    *   Pillow (用于图像处理)\n    *   Jupyter Notebook (可选，用于查看和运行演示)\n\n> **国内加速建议**：\n> 推荐使用清华源或阿里源安装 Python 包，以提升下载速度。\n> ```bash\n> pip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple \u003Cpackage_name>\n> ```\n\n## 安装步骤\n\n### 1. 克隆项目仓库\n首先，将教程代码下载到本地：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fsjchoi86\u002Fdl_tutorials.git\ncd dl_tutorials\n```\n\n### 2. 创建虚拟环境（推荐）\n为了避免依赖冲突，建议创建独立的虚拟环境：\n\n```bash\npython -m venv dl_env\n# Windows\ndl_env\\Scripts\\activate\n# macOS\u002FLinux\nsource dl_env\u002Fbin\u002Factivate\n```\n\n### 3. 安装依赖库\n根据教程内容，安装必要的深度学习库。由于该教程主要基于 TensorFlow 1.x 或早期 2.x 编写，建议先尝试安装兼容版本：\n\n```bash\n# 使用国内镜像源加速安装\npip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple tensorflow==1.15.0 numpy matplotlib pillow jupyter\n```\n\n*注：如果某些代码示例明确需要 TensorFlow 2.x，请将上述命令中的版本号调整为 `tensorflow` (最新版) 或特定版本，并根据代码报错信息调整 API 调用。*\n\n## 基本使用\n\n本教程的核心内容是 `presentations` 目录下的 PPT 课件以及对应的代码示例（通常命名为 `basic_*.py` 或在 PPT 中展示的代码片段）。\n\n### 1. 浏览课程大纲\n进入 `presentations` 目录，你可以按周次学习：\n*   **Week1**: 深度学习简介、Python 基础、MNIST 初探。\n*   **Week2**: CNN 原理、TensorFlow 基础、逻辑回归、Autoencoder。\n*   **Week3**: CNN 进阶、语义分割、自定义数据集训练。\n*   **Week4**: 目标检测 (RCNN\u002FYOLO)、RNN 基础、强化学习。\n*   **Week5**: RNN 应用、Word2Vec、图像描述生成。\n*   **Week6**: ResNet、神经风格迁移、GAN、对抗攻击。\n\n### 2. 运行第一个示例 (MNIST)\n以 Week1 中的 MNIST 手写数字识别为例，找到对应的代码文件（通常在根目录或子文件夹中搜索 `basic_mnist` 相关脚本）。\n\n假设你找到了 `basic_mnist.py` (若文件名不同，请替换为实际文件名)，运行命令如下：\n\n```bash\npython basic_mnist.py\n```\n\n如果教程中提供的是 Jupyter Notebook 格式或需要在 Notebook 中运行代码片段：\n\n```bash\njupyter notebook\n```\n然后在浏览器中导航至对应周的代码文件进行交互式运行。\n\n### 3. 使用自定义数据集\n在 Week2 和 Week3 中，教程介绍了如何生成和使用自己的数据集。你可以参考 `basic_gendataset` 相关的课件和代码，修改输入路径来训练你自己的图像模型：\n\n```bash\n# 示例：运行自定义数据集生成脚本（具体文件名请参考 Week2-1e 相关内容）\npython basic_gendataset.py --data_path .\u002Fmy_images\n```\n\n### 4. 可视化训练过程\n在 Week4 中，教程介绍了如何使用 TensorBoard 监控训练状态。运行训练脚本后，在终端执行：\n\n```bash\ntensorboard --logdir=.\u002Flogs\n```\n然后在浏览器访问 `http:\u002F\u002Flocalhost:6006` 查看损失曲线和模型结构。\n\n---\n**提示**：由于部分代码可能基于旧版 TensorFlow 语法（如 `tf.Session()`），若在 TensorFlow 2.x 环境下运行报错，可尝试在代码开头添加以下兼容模式代码：\n```python\nimport tensorflow.compat.v1 as tf\ntf.disable_v2_behavior()\n```","某高校人工智能实验室的研究生李明，正试图从零开始构建一个基于自定义数据集的医学图像分割模型，但他缺乏系统的深度学习实战经验。\n\n### 没有 dl_tutorials 时\n- **知识碎片化严重**：需要在 StackOverflow、博客和零散文档间反复跳转，难以理清从 Python 基础到 CNN 原理的逻辑脉络。\n- **环境搭建与代码调试耗时**：在配置 TensorFlow 环境和编写基础的 MNIST 测试代码上卡壳数天，无法快速验证想法。\n- **理论无法落地**：虽然读懂了 FCN 或 DeepLab 的论文公式，但面对“如何实现语义分割”的具体代码结构时毫无头绪。\n- **自定义数据束手无策**：不知道如何将医院提供的原始 DICOM 图像转换为模型可训练的格式，缺乏数据生成（Generate your own dataset）的指导。\n\n### 使用 dl_tutorials 后\n- **学习路径清晰连贯**：跟随 Week1 至 Week3 的渐进式课件，从 Python 基础平滑过渡到 CNN 核心概念，建立了完整的知识体系。\n- **快速上手实战**：直接复用 Week2 中现成的 MLP 和 Week3 中的简单 CNN 代码模板，半天内便跑通了基准测试。\n- **核心算法轻松复现**：依据 Week3 关于语义分割的详细教程，成功实现了基于 FCN 的分割网络，将论文理论转化为可运行代码。\n- **私有数据高效利用**：利用 Week2 和 Week3 中关于“构建自有数据集”的专项指导，顺利完成了医学图像的预处理与加载流程。\n\ndl_tutorials 通过提供从理论基础到代码复现的一站式教程，将李明原本需要数月的摸索期缩短为几周的高效开发周期。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsjchoi86_dl_tutorials_cf618a10.png","sjchoi86","Sungjoon","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fsjchoi86_40cae102.jpg","Associate professor at Korea University","Korea University","Seoul","sungjoon.s.choi@gmail.com",null,"https:\u002F\u002Fsites.google.com\u002Fview\u002Fsungjoon-choi","https:\u002F\u002Fgithub.com\u002Fsjchoi86",1522,394,"2026-04-10T17:42:09","MIT",1,"","未说明",{"notes":90,"python":88,"dependencies":91},"该项目主要为深度学习教学教程，内容涵盖 Python 基础、TensorFlow 基础、CNN、RNN 及各类经典模型（如 AlexNet, GoogLeNet, AlphaGo 等）的实现。README 中仅列出了 PPT 演示文稿链接，未提供具体的代码运行环境配置、依赖版本或硬件需求说明。根据内容推断，运行相关代码示例可能需要安装 TensorFlow 库，但具体版本需参考各周对应的实际代码文件（如有）。",[92],"TensorFlow",[15,14],"2026-03-27T02:49:30.150509","2026-04-20T12:53:05.690939",[],[]]