[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-ritchieng--deep-learning-wizard":3,"tool-ritchieng--deep-learning-wizard":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",140436,2,"2026-04-05T23:32:43",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":80,"owner_email":81,"owner_twitter":82,"owner_website":83,"owner_url":84,"languages":85,"stars":102,"forks":103,"last_commit_at":104,"license":105,"difficulty_score":23,"env_os":106,"env_gpu":107,"env_ram":106,"env_deps":108,"category_tags":121,"github_topics":122,"view_count":10,"oss_zip_url":129,"oss_zip_packed_at":129,"status":16,"created_at":130,"updated_at":131,"faqs":132,"releases":153},387,"ritchieng\u002Fdeep-learning-wizard","deep-learning-wizard","Open source guides\u002Fcodes for mastering deep learning to deploying deep learning in production in PyTorch, Python, Apptainer, and more.","deep-learning-wizard 是一套专注于深度学习的开源教程与代码集合，旨在帮助用户掌握从理论入门到生产环境部署的全流程技能。它基于 PyTorch 和 Python 构建，内容广泛覆盖机器学习、深度学习、深度强化学习以及数据工程等领域。\n\n面对海量且零散的深度学习资料，学习者常感到无从下手或难以将模型落地。deep-learning-wizard 通过结构化的课程路径，有效解决了知识碎片化问题。从基础的矩阵运算、梯度推导，到卷积神经网络、循环神经网络等主流架构，再到强化学习与模型优化策略，内容层层递进。特别值得一提的是，它提供了从零手推算法的实现细节，并包含容器化部署（Apptainer）等工程实践，填补了理论与实战之间的鸿沟。\n\n这套资源非常适合人工智能开发者、算法研究人员以及计算机专业学生使用。其配套网站支持移动端访问，便于灵活学习。尽管项目仍在持续完善中，但目前已积累的丰富 Jupyter 笔记本和文档，已成为深度学习领域极具价值的免费学习宝库。","# Deep Learning Materials by Deep Learning Wizard\n\n\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-green.svg\"\u002F>\n\n[![DOI](https:\u002F\u002Fzenodo.org\u002Fbadge\u002F139945544.svg)](https:\u002F\u002Fzenodo.org\u002Fbadge\u002Flatestdoi\u002F139945544)\n\n## Start Learning Now\n\nPlease head to [www.deeplearningwizard.com](https:\u002F\u002Fwww.deeplearningwizard.com\u002F) to start learning! It is mobile\u002Ftablet friendly and open-source.\n\n## Repository Details\n\nThis repository contains all the notebooks and mkdocs markdown files of the tutorials covering machine learning, deep learning, deep reinforcement learning, data engineering, general programming, and visualizations powering the website.\n\nTake note this is an early work in progress, do be patient as we gradually upload our guides.\n\n## Sections and Subsections\n\n- Deep Learning and Deep Reinforcement Learning Tutorials (Libraries: Python, PyTorch, Gym, NumPy, Matplotlib and more)\n    - [Introduction](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fintro\u002F)\n    - [Course Progression](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fcourse_progression\u002F)\n    - Practical Deep Learning with PyTorch\n      - [Matrices](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_matrices\u002F)\n      - [Gradients](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_gradients\u002F)\n      - [Linear Regression](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_linear_regression\u002F)\n      - [Logistic Regression](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_logistic_regression\u002F)\n      - [Feedforward Neural Network (FNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_feedforward_neuralnetwork\u002F)\n      - [Convolutional Neural Network (CNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_convolutional_neuralnetwork\u002F)\n      - [Recurrent Neural Network (RNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_recurrent_neuralnetwork\u002F)\n      - [Long Short-Term Memory Network (LSTM)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_lstm_neuralnetwork\u002F)\n      - [Autoencoders (AE)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_autoencoder\u002F)\n      - [Fully Connected Overcomplete Autoencoders](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_fc_overcomplete_ae\u002F)\n    - Improving Deep Learning with PyTorch\n      - [Derivative, Gradient and Jacobian](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fderivative_gradient_jacobian\u002F)\n      - [Forward- and Backward-propagation and Gradient Descent (From Scratch FNN Regression)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fforwardpropagation_backpropagation_gradientdescent\u002F)\n      - [Learning Rate Scheduling](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Flr_scheduling\u002F)\n      - [Optimization Algorithms](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Foptimizers\u002F)\n      - [Weight Initialization and Activation Functions](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fweight_initialization_activation_functions\u002F)\n    - Deep Reinforcement Learning with PyTorch\n      - [Supervised to Reinforcement Learning](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fsupervised_to_rl\u002F)\n      - [Markov Decision Processes and Bellman Equations](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fbellman_mdp\u002F)\n      - [Dynamic Programming](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fdynamic_programming_frozenlake\u002F)\n    - From Scratch Deep Learning with PyTorch\u002FPython\n      - [From Scratch Logistic Regression Classification](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Ffromscratch\u002Ffromscratch_logistic_regression\u002F)\n    - Compute Optimization\n      - [Speed Optimization Basics Numba](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fproduction_pytorch\u002Fspeed_optimization_basics_numba\u002F)\n\n- Language Models (Libraries: Python, Pytorch, Ollama, LlamaIndex, CUDA, Huggingface, Apptainer)\n  - [Intro](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Fintro\u002F)\n  - Containers\n    - [HPC Containers with Apptainer](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Fcontainers\u002Fhpc_containers_apptainer\u002F)\n  - Language Models\n    - [LLM Introduction & Hyperparameter Tuning](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Fllm\u002Fllm_intro_hyperparameter_tuning\u002F)\n  - Multi-Modal Language Models\n    - [MMLM Introduction](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Fmmlm\u002Fmmlm_intro\u002F)\n  - Retrieval Augemented Generation (RAG)\n    - [Embeddings Introduction](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Frag\u002Fembedding\u002F)\n\n- Machine Learning Tutorials (Libraries: Python, cuDF RAPIDS, cuML RAPIDS, pandas, numpy, scikit-learn and more)\n  - RAPIDS cuDF\n    - [Intro](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fmachine_learning\u002Fintro\u002F)\n    - [GPU DataFrames](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fmachine_learning\u002Fgpu\u002Frapids_cudf\u002F)\n    - [CPU\u002FGPU Fractional Differencing](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fmachine_learning\u002Fgpu\u002Fgpu_fractional_differencing\u002F)\n  \n- Programming Tutorials (Libraries: C++, Python, Bash and more)\n  - [Intro](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fintro\u002F)\n  - [C++](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fcpp\u002Fcpp\u002F)\n  - [Bash](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fbash\u002Fbash\u002F)\n  - [Python](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fpython\u002Fpython\u002F)\n  - [Javascript](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fjavascript\u002Fjavascript\u002F)\n  - [Electron](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Felectron\u002Felectron\u002F)\n\n- Data Engineering Tutorials (Libraries: Bash, Databricks, Delta Live Tables, Parquet, Python, Cassandra, and more)\n  - Cassandra (NoSQL)\n    - [Introduction](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdata_engineering\u002Fnosql\u002Fcassandra\u002Fintro\u002F)\n    - [Apache Cassandra Cluster Setup](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdata_engineering\u002Fnosql\u002Fcassandra\u002Fsetting_up_cluster\u002F)\n    \n## About Deep Learning Wizard\nWe deploy a top-down approach that enables you to grasp deep learning theories and code easily and quickly. We have open-sourced all our materials through our Deep Learning Wizard Wikipedia. For visual learners, feel free to sign up for our video course and join thousands of deep learning wizards.\n\nTo this date, we have taught thousands of students across more than 120+ countries.\n\n## Contribution\nWe are openly calling people to contribute to this repository for errors. Feel free to create a pull request.\n\n## Main Contributor\n[Ritchie Ng](https:\u002F\u002Fgithub.com\u002Fritchieng)\n\n## Editors and Supporters\n- [Jie Fu, Editor (Postdoc in Montreal Institute for Learning Algorithms (MILA))](https:\u002F\u002Fgithub.com\u002Fbigaidream)\n- [Alfredo Canziani, Supporter (Assistant Prof in NYU under Yann Lecun)](https:\u002F\u002Fgithub.com\u002FAtcold)\n- [Marek Bardonski, Supporter (Managing Partner, AIRev)](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fmarek-bardonski\u002F)\n\n## Bugs and Improvements\nFeel free to report bugs and improvements via issues. Or just simply try to pull to make any improvements\u002Fcorrections.\n\n## Social Media\n- [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCJz2MIjiCosOQCwhnsYxeEw)\n- [Twitter](https:\u002F\u002Ftwitter.com\u002Fdeeplearningwiz)\n- [Facebook](https:\u002F\u002Fwww.facebook.com\u002FDeepLearningWizard\u002F)\n- [Linkedin](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fdeeplearningwizard\u002F)\n\n## Citation\nIf you find the materials useful, like the diagrams or content, feel free to cite this repository.\n\n[![DOI](https:\u002F\u002Fzenodo.org\u002Fbadge\u002F139945544.svg)](https:\u002F\u002Fzenodo.org\u002Fbadge\u002Flatestdoi\u002F139945544)\n","# Deep Learning Wizard 的深度学习资料\n\n\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-green.svg\"\u002F>\n\n[![DOI](https:\u002F\u002Fzenodo.org\u002Fbadge\u002F139945544.svg)](https:\u002F\u002Fzenodo.org\u002Fbadge\u002Flatestdoi\u002F139945544)\n\n## 立即开始学习\n\n请访问 [www.deeplearningwizard.com](https:\u002F\u002Fwww.deeplearningwizard.com\u002F) 开始学习！它支持移动设备和平板电脑，并且是开源的。\n\n## 仓库详情\n\n此仓库包含所有教程的 notebook 和 mkdocs 文档文件，涵盖机器学习 (Machine Learning)、深度学习 (Deep Learning)、深度强化学习 (Deep Reinforcement Learning)、数据工程 (Data Engineering)、通用编程以及支撑网站的数据可视化。\n\n请注意，这是一个早期的进行中项目，请耐心等候我们逐步上传指南。\n\n## 章节与子章节\n\n- 深度学习与深度强化学习教程 (库：Python, PyTorch, Gym, NumPy, Matplotlib 等)\n    - [介绍](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fintro\u002F)\n    - [课程进度](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fcourse_progression\u002F)\n    - 使用 PyTorch 进行实践深度学习\n      - [矩阵](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_matrices\u002F)\n      - [梯度](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_gradients\u002F)\n      - [线性回归](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_linear_regression\u002F)\n      - [逻辑回归](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_logistic_regression\u002F)\n      - [前馈神经网络 (FNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_feedforward_neuralnetwork\u002F)\n      - [卷积神经网络 (CNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_convolutional_neuralnetwork\u002F)\n      - [循环神经网络 (RNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_recurrent_neuralnetwork\u002F)\n      - [长短期记忆网络 (LSTM)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_lstm_neuralnetwork\u002F)\n      - [自编码器 (AE)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_autoencoder\u002F)\n      - [全连接过完备自编码器](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_fc_overcomplete_ae\u002F)\n    - 使用 PyTorch 改进深度学习\n      - [导数、梯度和雅可比矩阵](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fderivative_gradient_jacobian\u002F)\n      - [前向传播与反向传播及梯度下降（从零开始的 FNN 回归）](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fforwardpropagation_backpropagation_gradientdescent\u002F)\n      - [学习率调度](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Flr_scheduling\u002F)\n      - [优化算法](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Foptimizers\u002F)\n      - [权重初始化与激活函数](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fweight_initialization_activation_functions\u002F)\n    - 使用 PyTorch 进行深度强化学习\n      - [从监督学习到强化学习](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fsupervised_to_rl\u002F)\n      - [马尔可夫决策过程与贝尔曼方程](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fbellman_mdp\u002F)\n      - [动态规划](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fdynamic_programming_frozenlake\u002F)\n    - 使用 PyTorch\u002FPython 从零开始深度学习\n      - [从零开始的逻辑回归分类](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Ffromscratch\u002Ffromscratch_logistic_regression\u002F)\n    - 计算优化\n      - [Numba 基础速度优化](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fproduction_pytorch\u002Fspeed_optimization_basics_numba\u002F)\n\n- 语言模型 (库：Python, Pytorch, Ollama, LlamaIndex, CUDA, Huggingface, Apptainer)\n  - [简介](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Fintro\u002F)\n  - 容器\n    - [使用 Apptainer 的高性能计算 (HPC) 容器](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Fcontainers\u002Fhpc_containers_apptainer\u002F)\n  - 语言模型\n    - [大语言模型 (LLM) 介绍与超参数调整](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Fllm\u002Fllm_intro_hyperparameter_tuning\u002F)\n  - 多模态语言模型\n    - [多模态语言模型介绍](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Fmmlm\u002Fmmlm_intro\u002F)\n  - 检索增强生成 (RAG)\n    - [嵌入向量介绍](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Frag\u002Fembedding\u002F)\n\n- 机器学习教程 (库：Python, cuDF RAPIDS, cuML RAPIDS, pandas, numpy, scikit-learn 等)\n  - RAPIDS cuDF\n    - [简介](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fmachine_learning\u002Fintro\u002F)\n    - [GPU 数据框](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fmachine_learning\u002Fgpu\u002Frapids_cudf\u002F)\n    - [CPU\u002FGPU 分数差分](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fmachine_learning\u002Fgpu\u002Fgpu_fractional_differencing\u002F)\n  \n- 编程教程 (库：C++, Python, Bash 等)\n  - [简介](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fintro\u002F)\n  - [C++](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fcpp\u002Fcpp\u002F)\n  - [Bash](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fbash\u002Fbash\u002F)\n  - [Python](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fpython\u002Fpython\u002F)\n  - [Javascript](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fjavascript\u002Fjavascript\u002F)\n  - [Electron](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Felectron\u002Felectron\u002F)\n\n- 数据工程教程 (库：Bash, Databricks, Delta Live Tables, Parquet, Python, Cassandra 等)\n  - Cassandra (非关系型数据库 (NoSQL))\n    - [介绍](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdata_engineering\u002Fnosql\u002Fcassandra\u002Fintro\u002F)\n    - [Apache Cassandra 集群设置](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdata_engineering\u002Fnosql\u002Fcassandra\u002Fsetting_up_cluster\u002F)\n    \n## 关于 Deep Learning Wizard\n我们采用自上而下的方法，让您能够轻松快速地掌握深度学习理论和代码。我们通过 Deep Learning Wizard Wiki 开源了所有材料。对于视觉学习者，欢迎注册我们的视频课程，加入数千名深度学习巫师行列。\n\n迄今为止，我们已在 120 多个国家教授了数千名学生。\n\n## 贡献\n我们公开呼吁人们为此仓库的错误做出贡献。欢迎创建拉取请求 (Pull Request)。\n\n## 主要贡献者\n[Ritchie Ng](https:\u002F\u002Fgithub.com\u002Fritchieng)\n\n## 编辑与支持者\n- [Jie Fu，编辑（蒙特利尔学习算法研究所 (MILA) 博士后）](https:\u002F\u002Fgithub.com\u002Fbigaidream)\n- [Alfredo Canziani，支持者（NYU 助理教授，师从 Yann Lecun）](https:\u002F\u002Fgithub.com\u002FAtcold)\n- [Marek Bardonski，支持者（AIRev 管理合伙人）](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fmarek-bardonski\u002F)\n\n## 错误与改进\n欢迎通过 Issue (问题) 报告错误和改进建议。或者直接尝试提交 Pull Request (拉取请求) 来进行任何改进或修正。\n\n## 社交媒体\n- [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCJz2MIjiCosOQCwhnsYxeEw)\n- [Twitter](https:\u002F\u002Ftwitter.com\u002Fdeeplearningwiz)\n- [Facebook](https:\u002F\u002Fwww.facebook.com\u002FDeepLearningWizard\u002F)\n- [LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fdeeplearningwizard\u002F)\n\n## 引用\n如果您发现这些材料有用，例如图表或内容，欢迎引用此仓库。\n\n[![DOI](https:\u002F\u002Fzenodo.org\u002Fbadge\u002F139945544.svg)](https:\u002F\u002Fzenodo.org\u002Fbadge\u002Flatestdoi\u002F139945544)","# deep-learning-wizard 快速上手指南\n\n**deep-learning-wizard** 是一个开源的深度学习教学资源库，涵盖机器学习、深度学习、强化学习及编程教程。本工具主要通过网站和 Jupyter Notebook 提供交互式学习体验。\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 \u002F macOS \u002F Windows\n- **Python 版本**: 3.6+\n- **核心依赖库**:\n  - `pytorch` (用于深度学习与强化学习教程)\n  - `numpy`, `matplotlib` (数据处理与可视化)\n  - `jupyter` (用于本地运行 Notebook)\n  - `gym` (强化学习部分需要)\n- **硬件建议**: 若运行 GPU 加速教程（如 CNN, LLM），建议配备 NVIDIA 显卡并安装对应版本的 CUDA 驱动。\n\n## 安装步骤\n\n由于本项目主要为教学材料仓库，您无需通过包管理器安装，可通过以下方式获取资源：\n\n### 方式一：访问在线网站（推荐）\n直接访问官方文档网站即可开始学习，支持移动端和平板设备。\n```bash\n# 打开浏览器访问\nhttps:\u002F\u002Fwww.deeplearningwizard.com\u002F\n```\n\n### 方式二：克隆本地仓库\n如需离线阅读或运行本地 Jupyter Notebook，请克隆代码仓库。\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fritchieng\u002Fdeep-learning-wizard.git\ncd deep-learning-wizard\n```\n> **提示**: 国内网络环境下，建议使用 GitHub 镜像源加速克隆过程。\n\n## 基本使用\n\n### 1. 启动 Jupyter Notebook\n克隆仓库后，进入项目目录并启动 Notebook 服务：\n```bash\njupyter notebook\n```\n随后在浏览器中打开生成的链接，即可浏览和运行 `.ipynb` 文件中的教程代码。\n\n### 2. 运行特定教程\n根据您的需求选择对应的模块进行深入学习：\n- **深度学习基础**: 查看 `practical_pytorch` 文件夹下的线性回归、神经网络等示例。\n- **强化学习**: 参考 `deep_reinforcement_learning_pytorch` 模块。\n- **大语言模型**: 查阅 `language_model` 相关教程（需额外配置 Ollama, Huggingface 等环境）。\n\n### 3. 贡献与反馈\n如果您发现内容错误或希望改进，欢迎提交 Pull Request 或创建 Issue。\n```bash\n# 修改代码后提交\ngit add .\ngit commit -m \"fix: update tutorial content\"\ngit push origin main\n```","某电商公司的初级算法工程师小张负责开发商品图像识别系统，急需将 PyTorch 模型从实验环境迁移至生产服务器。面对紧迫的项目周期，他迫切需要一套能兼顾理论与工程实践的学习资源。\n\n### 没有 deep-learning-wizard 时\n- 阅读官方文档晦涩难懂，对反向传播公式如何转化为 PyTorch 代码感到困惑。\n- 模型训练时损失不下降，排查数小时才发现是权重初始化策略选错了。\n- 部署阶段因缺少 Docker 或 Apptainer 经验，导致服务器环境依赖报错，项目延期。\n\n### 使用 deep-learning-wizard 后\n- 直接参考 deep-learning-wizard“从 Scratch 构建神经网络”章节，快速复现了包含前向与反向传播的核心代码逻辑。\n- 根据 deep-learning-wizard“优化算法”和“权重初始化”指南，调整了参数配置，使模型收敛速度提升了 50%。\n- 按照 deep-learning-wizard 中的生产部署指南配置 Apptainer 容器，一次性解决了 GPU 驱动与 Python 版本的兼容性问题。\n\ndeep-learning-wizard 通过结构化的实战代码与部署方案，帮助开发者高效跨越从理论认知到工程落地的鸿沟。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fritchieng_deep-learning-wizard_21c1a561.png","ritchieng","Ritchie Ng","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fritchieng_1edc2eaa.jpg","Notes: ritchieng.com • Guides: deeplearningwizard.com","Imperial College London | NUS","Singapore","ritchieng@u.nus.edu","RitchieNg","ritchieng.com","https:\u002F\u002Fgithub.com\u002Fritchieng",[86,90,94,98],{"name":87,"color":88,"percentage":89},"Python","#3572A5",48,{"name":91,"color":92,"percentage":93},"HTML","#e34c26",46.6,{"name":95,"color":96,"percentage":97},"JavaScript","#f1e05a",5.2,{"name":99,"color":100,"percentage":101},"Shell","#89e051",0.2,871,235,"2026-04-04T05:43:34","MIT","未说明","需要 NVIDIA GPU (部分教程涉及 CUDA\u002FRAPIDS), 具体型号及显存大小未说明",{"notes":109,"python":106,"dependencies":110},"本仓库主要为教程资料（Notebooks\u002FMkDocs），非独立安装包。不同章节（如 RAPIDS、LLM）对环境和硬件要求不同，需根据具体教程配置环境。",[111,112,113,114,115,116,117,118,119,120],"PyTorch","NumPy","Pandas","Scikit-learn","Gym","Matplotlib","Huggingface","Ollama","LlamaIndex","cuDF RAPIDS",[26,13],[123,124,125,126,127,128],"pytorch","deep-learning","apptainer","llamaindex","ollama","python3",null,"2026-03-27T02:49:30.150509","2026-04-06T09:44:32.366742",[133,138,143,148],{"id":134,"question_zh":135,"answer_zh":136,"source_url":137},1414,"如何在 Markdown 文件中渲染特殊效果（如沙漏图标）？","这些效果依赖于 Material mkdocs 主题。请在 Markdown 代码中使用特定的 Emoji 语法，例如 `:hourglass_flowing_sand:`。你需要确保安装了该主题。参考文件：https:\u002F\u002Fgithub.com\u002Fritchieng\u002Fdeep-learning-wizard\u002Fblob\u002Fmaster\u002Fdocs\u002Fdeep_learning\u002Fcourse_progression.md","https:\u002F\u002Fgithub.com\u002Fritchieng\u002Fdeep-learning-wizard\u002Fissues\u002F12",{"id":139,"question_zh":140,"answer_zh":141,"source_url":142},1415,"在 Google Colab 中是否需要手动安装 cuDF？","不需要。cuDF 现在已在 Colab 环境中预装。相关的 cuDF Colab Notebook 已更新以反映这一变化，用户可直接使用而无需执行额外的安装命令。","https:\u002F\u002Fgithub.com\u002Fritchieng\u002Fdeep-learning-wizard\u002Fissues\u002F23",{"id":144,"question_zh":145,"answer_zh":146,"source_url":147},1416,"RAPIDS-Colab 教程中的安装脚本是否过时了？如何获取最新模板？","是的，旧的安装脚本已过时。RAPIDS 已升级到更可靠的综合安装脚本。请使用新的安装模板链接：https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1TAAi_szMfWqRfHVfjGSqnGVLr_ztzUM9#scrollTo=CtNdk7PSafKP","https:\u002F\u002Fgithub.com\u002Fritchieng\u002Fdeep-learning-wizard\u002Fissues\u002F9",{"id":149,"question_zh":150,"answer_zh":151,"source_url":152},1417,"在 Colab 中安装 RAPIDS 包推荐使用 Conda 还是 Pip？","推荐使用更快且更干净的 pip 安装方式。但如果需要 cuxfilter、cusignal 或 cuspatial 等特定包，可以使用旧的 conda 安装方式。","https:\u002F\u002Fgithub.com\u002Fritchieng\u002Fdeep-learning-wizard\u002Fissues\u002F19",[154,159,164,169],{"id":155,"version":156,"summary_zh":157,"released_at":158},110594,"v1.0.3","## Highlights\r\n\r\nCleaned all sections and included new Apptainer guide for HPC compute containerization and LLM introduction and hyperparameter tuning with Gemma 7b (Google) model.\r\n\r\n## Sections and Subsections\r\n\r\n- Deep Learning and Deep Reinforcement Learning Tutorials (Libraries: Python, PyTorch, Gym, NumPy, Matplotlib and more)\r\n    - [Introduction](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fintro\u002F)\r\n    - [Course Progression](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fcourse_progression\u002F)\r\n    - Practical Deep Learning with PyTorch\r\n      - [Matrices](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_matrices\u002F)\r\n      - [Gradients](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_gradients\u002F)\r\n      - [Linear Regression](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_linear_regression\u002F)\r\n      - [Logistic Regression](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_logistic_regression\u002F)\r\n      - [Feedforward Neural Network (FNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_feedforward_neuralnetwork\u002F)\r\n      - [Convolutional Neural Network (CNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_convolutional_neuralnetwork\u002F)\r\n      - [Recurrent Neural Network (RNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_recurrent_neuralnetwork\u002F)\r\n      - [Long Short-Term Memory Network (LSTM)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_lstm_neuralnetwork\u002F)\r\n      - [Autoencoders (AE)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_autoencoder\u002F)\r\n      - [Fully Connected Overcomplete Autoencoders](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_fc_overcomplete_ae\u002F)\r\n    - Improving Deep Learning with PyTorch\r\n      - [Derivative, Gradient and Jacobian](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fderivative_gradient_jacobian\u002F)\r\n      - [Forward- and Backward-propagation and Gradient Descent (From Scratch FNN Regression)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fforwardpropagation_backpropagation_gradientdescent\u002F)\r\n      - [Learning Rate Scheduling](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Flr_scheduling\u002F)\r\n      - [Optimization Algorithms](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Foptimizers\u002F)\r\n      - [Weight Initialization and Activation Functions](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fweight_initialization_activation_functions\u002F)\r\n    - Deep Reinforcement Learning with PyTorch\r\n      - [Supervised to Reinforcement Learning](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fsupervised_to_rl\u002F)\r\n      - [Markov Decision Processes and Bellman Equations](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fbellman_mdp\u002F)\r\n      - [Dynamic Programming](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fdynamic_programming_frozenlake\u002F)\r\n    - From Scratch Deep Learning with PyTorch\u002FPython\r\n      - [From Scratch Logistic Regression Classification](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Ffromscratch\u002Ffromscratch_logistic_regression\u002F)\r\n    - Compute Optimization\r\n      - [Speed Optimization Basics Numba](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fproduction_pytorch\u002Fspeed_optimization_basics_numba\u002F)\r\n\r\n- Language Models (Libraries: Python, Pytorch, Ollama, LlamaIndex, CUDA, Huggingface, Apptainer)\r\n  - [Intro](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Fintro\u002F)\r\n  - Containers\r\n    - [HPC Containers with Apptainer](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Fcontainers\u002Fhpc_containers_apptainer\u002F)\r\n  - Language Models\r\n    - [LLM Introduction & Hyperparameter Tuning](https:\u002F\u002Fwww.deeplearningwizard.com\u002Flanguage_model\u002Fllm\u002Fllm_intro_hyperparameter_tuning\u002F)\r\n\r\n- Machine Learning Tutorials (Libraries: Python, cuDF RAPIDS, cuML RAPIDS, pandas, numpy, scikit-learn and more)\r\n  - RAPIDS cuDF\r\n    - [Intro](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fmachine_learning\u002Fintro\u002F)\r\n    - [GPU DataFrames](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fmachine_learning\u002Fgpu\u002Frapids_cudf\u002F)\r\n    - [CPU\u002FGPU Fractional Differencing](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fmachine_learning\u002Fgpu\u002Fgpu_fractional_differencing\u002F)\r\n  \r\n- Programming Tutorials (Libraries: C++, Python, Bash and more)\r\n  - [Intro](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fintro\u002F)\r\n  - [C++](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fcpp\u002Fcpp\u002F)\r\n  - [Bash](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fbash\u002Fbash\u002F)\r\n  - [Python](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fpython\u002Fpython\u002F)\r\n  - [Javascript](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fjavascript\u002Fjavascript\u002F)\r\n  - [Electron](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogr","2024-02-26T12:34:44",{"id":160,"version":161,"summary_zh":162,"released_at":163},110595,"v1.0.2","## Highlights\r\nCleaned documentation, code, and website with a particular emphasis on sections and subsections to demarcate tutorials for ease of learning and ensure scalability in their respective sections.\r\n\r\n## Sections and Subsections\r\n- Deep Learning and Deep Reinforcement Learning Tutorials (Libraries: Python, PyTorch, Gym, NumPy, Matplotlib and more)\r\n    - [Introduction](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fintro\u002F)\r\n    - [Course Progression](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fcourse_progression\u002F)\r\n    - Practical Deep Learning with PyTorch\r\n      - [Matrices](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_matrices\u002F)\r\n      - [Gradients](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_gradients\u002F)\r\n      - [Linear Regression](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_linear_regression\u002F)\r\n      - [Logistic Regression](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_logistic_regression\u002F)\r\n      - [Feedforward Neural Network (FNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_feedforward_neuralnetwork\u002F)\r\n      - [Convolutional Neural Network (CNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_convolutional_neuralnetwork\u002F)\r\n      - [Recurrent Neural Network (RNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_recurrent_neuralnetwork\u002F)\r\n      - [Long Short-Term Memory Network (LSTM)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_lstm_neuralnetwork\u002F)\r\n      - [Autoencoders (AE)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_autoencoder\u002F)\r\n      - [Fully Connected Overcomplete Autoencoders](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_fc_overcomplete_ae\u002F)\r\n    - Improving Deep Learning with PyTorch\r\n      - [Derivative, Gradient and Jacobian](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fderivative_gradient_jacobian\u002F)\r\n      - [Forward- and Backward-propagation and Gradient Descent (From Scratch FNN Regression)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fforwardpropagation_backpropagation_gradientdescent\u002F)\r\n      - [Learning Rate Scheduling](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Flr_scheduling\u002F)\r\n      - [Optimization Algorithms](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Foptimizers\u002F)\r\n      - [Weight Initialization and Activation Functions](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fweight_initialization_activation_functions\u002F)\r\n    - Deep Reinforcement Learning with PyTorch\r\n      - [Supervised to Reinforcement Learning](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fsupervised_to_rl\u002F)\r\n      - [Markov Decision Processes and Bellman Equations](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fbellman_mdp\u002F)\r\n      - [Dynamic Programming](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fdynamic_programming_frozenlake\u002F)\r\n    - From Scratch Deep Learning with PyTorch\u002FPython\r\n      - [From Scratch Logistic Regression Classification](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Ffromscratch\u002Ffromscratch_logistic_regression\u002F)\r\n    - Compute Optimization\r\n      - [Speed Optimization Basics Numba](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fproduction_pytorch\u002Fspeed_optimization_basics_numba\u002F)\r\n\r\n- Machine Learning Tutorials (Libraries: Python, cuDF RAPIDS, cuML RAPIDS, pandas, numpy, scikit-learn and more)\r\n  - RAPIDS cuDF\r\n    - [Intro](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fmachine_learning\u002Fintro\u002F)\r\n    - [GPU DataFrames](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fmachine_learning\u002Fgpu\u002Frapids_cudf\u002F)\r\n    - [CPU\u002FGPU Fractional Differencing](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fmachine_learning\u002Fgpu\u002Fgpu_fractional_differencing\u002F)\r\n  \r\n- Programming Tutorials (Libraries: C++, Python, Bash and more)\r\n  - [Intro](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fintro\u002F)\r\n  - [C++](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fcpp\u002Fcpp\u002F)\r\n  - [Bash](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fbash\u002Fbash\u002F)\r\n  - [Python](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fpython\u002Fpython\u002F)\r\n  - [Javascript](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fjavascript\u002Fjavascript\u002F)\r\n  - [Electron](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Felectron\u002Felectron\u002F)\r\n\r\n- Data Engineering Tutorials (Libraries: Bash, Databricks, Delta Live Tables, Parquet, Python, Cassandra, and more)\r\n  - Cassandra (NoSQL)\r\n    - [Introduction](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdata_engineering\u002Fnosql\u002Fcassandra\u002Fintro\u002F)\r\n    - [Apache Cassandra Cluster Setup](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdata_engineering\u002Fnosql\u002Fcassandra\u002Fsetting_up_cluster\u002F)\r\n","2023-10-03T02:09:39",{"id":165,"version":166,"summary_zh":167,"released_at":168},110596,"v1.0.1","## Highlights\r\n\r\nStable releases for deep learning tutorials. And initial launch of deep reinforcement learning, scalable database and programming tutorials. \r\n\r\n## Stable Sections and Subsections\r\n- [Deep Learning and Deep Reinforcement Learning Tutorials (Libraries: Python, PyTorch, Gym, NumPy and Matplotlib)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fintro\u002F)\r\n    - [Course Progression](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fcourse_progression\u002F)\r\n    - [Matrices](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_matrices\u002F)\r\n    - [Gradients](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_gradients\u002F)\r\n    - [Linear Regression](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_linear_regression\u002F)\r\n    - [Logistic Regression](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_logistic_regression\u002F)\r\n    - [Feedforward Neural Network](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_feedforward_neuralnetwork\u002F)\r\n    - [Convolutional Neural Network (CNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_convolutional_neuralnetwork\u002F)\r\n    - [Recurrent Neural Network (RNN)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_recurrent_neuralnetwork\u002F)\r\n    - [Long Short-Term Memory (LSTM) network](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fpractical_pytorch\u002Fpytorch_lstm_neuralnetwork\u002F)\r\n    - [Derivative, Gradient and Jacobian](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fderivative_gradient_jacobian\u002F)\r\n    - [Forwardpropagation, Backpropagation and Gradient Descent](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fforwardpropagation_backpropagation_gradientdescent\u002F)\r\n    - [Learning Rate Scheduling](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Flr_scheduling\u002F)\r\n    - [Optimization Algorithms](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Foptimizers\u002F)\r\n    - [Weight Initialization and Activation Functions](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fboosting_models_pytorch\u002Fweight_initialization_activation_functions\u002F)\r\n    - [Supervised to Reinforcement Learning](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fsupervised_to_rl\u002F)\r\n    - [Markov Decision Processes and Bellman Equations](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fbellman_mdp\u002F)\r\n    - [Dynamic Programming](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdeep_learning\u002Fdeep_reinforcement_learning_pytorch\u002Fdynamic_programming_frozenlake\u002F)\r\n- [Programming Tutorials (Libraries: C++, Python, Bash and more)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fintro\u002F)\r\n    - [C++](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fprogramming\u002Fcpp\u002Fcpp\u002F)\r\n- [Scalable Database Tutorials (Libraries: Apache Cassandra, Bash and Python)](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdatabase\u002Fintro\u002F)\r\n    - [Apache Cassandra Cluster Setup](https:\u002F\u002Fwww.deeplearningwizard.com\u002Fdatabase\u002Fsetting_up_cluster\u002F)","2019-04-18T08:55:36",{"id":170,"version":171,"summary_zh":172,"released_at":173},110597,"v1.0.0","## About This Release\r\nAfter careful deliberation, I have decided to gradually open-source our written deep learning materials that I have used to teach more than 3000 students worldwide across 120 countries through my [video course, Practical Deep Learning with Pytorch](https:\u002F\u002Fwww.udemy.com\u002Fpractical-deep-learning-with-pytorch\u002F?couponCode=DEEPWIZARD).\r\n\r\nAs this is a very new effort to open-source my materials, it's still a work-in-progress. Please bear with me while I clean it up.\r\n\r\nThis repository powers the main open-source Deep Learning Wizard website [www.deeplearningwizard.com](https:\u002F\u002Fwww.deeplearningwizard.com\u002F) and contains the materials for the following topics.\r\n\r\n## Topics Covered\r\n- PyTorch Fundamentals - Matrices\r\n- PyTorch Fundamentals - Gradients\r\n- PyTorch Fundamentals - Linear Regression\r\n- PyTorch Fundamentals - Logistic Regression\r\n- PyTorch Fundamentals - Feedforward Neural Network\r\n\r\n## Always Latest PyTorch Version\r\nWe always provide the latest PyTorch version (currently 0.4 or 1.0 pre-release) so that you will be learning up-to-date code! \r\n\r\n## About Deep Learning Wizard\r\nWe deploy a top-down approach that enables you to grasp deep learning theories and code easily and quickly. We have open-sourced all our materials through our Deep Learning Wizard Wikipedia. For visual learners, feel free to sign up for our video course and join over 2300 deep learning wizards.\r\n\r\nTo this date, we have taught thousands of students across more than 120+ countries from students as young as 15 to postgraduates and professionals in leading MNCs and research institutions around the world.\r\n\r\n## Contribution\r\nWe are openly calling people to contribute to this repository for errors. Feel free to create a pull request.","2018-11-08T14:03:38"]