[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-Amin-Tgz--awesome-tensorflow-2":3,"tool-Amin-Tgz--awesome-tensorflow-2":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",138956,2,"2026-04-05T11:33:21",[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":83,"owner_url":84,"languages":83,"stars":85,"forks":86,"last_commit_at":87,"license":88,"difficulty_score":89,"env_os":90,"env_gpu":91,"env_ram":90,"env_deps":92,"category_tags":97,"github_topics":98,"view_count":23,"oss_zip_url":83,"oss_zip_packed_at":83,"status":16,"created_at":114,"updated_at":115,"faqs":116,"releases":117},2480,"Amin-Tgz\u002Fawesome-tensorflow-2","awesome-tensorflow-2","👉 Tensorflow 2.x resources such as tutorial, blog, code and videos","awesome-tensorflow-2 是一个专为 TensorFlow 2.x 生态系统打造的精选资源合集。它系统地整理了涵盖教程、技术博客、示例代码、视频课程以及相关书籍的高质量学习材料，旨在帮助开发者更高效地掌握这一主流深度学习框架。\n\nTensorFlow 2.x 相比早期版本进行了重大重构，强调“简洁易用”和“即时执行（Eager Execution）”，并统一了 API 接口。然而，版本的快速迭代也带来了学习曲线陡峭、旧资料失效以及迁移困难等问题。awesome-tensorflow-2 正是为了解决这些痛点而生，它通过人工筛选和分类，剔除了过时或低质量的内容，为用户提供了一条清晰的学习路径。无论是官方文档的补充解读，还是针对特定任务（如生成对抗网络 GAN、强化学习 RL、自然语言处理 NLP 及目标检测）的实战项目，这里都能找到对应的优质资源。\n\n这份合集特别适合人工智能领域的开发者、数据科学家、研究人员以及正在从 TensorFlow 1.x 迁移至 2.x 的技术人员。对于初学者，它提供了从基础入门到进阶实战的系统化教程；对于资深从业者，它则是获取最新技术动态、最","awesome-tensorflow-2 是一个专为 TensorFlow 2.x 生态系统打造的精选资源合集。它系统地整理了涵盖教程、技术博客、示例代码、视频课程以及相关书籍的高质量学习材料，旨在帮助开发者更高效地掌握这一主流深度学习框架。\n\nTensorFlow 2.x 相比早期版本进行了重大重构，强调“简洁易用”和“即时执行（Eager Execution）”，并统一了 API 接口。然而，版本的快速迭代也带来了学习曲线陡峭、旧资料失效以及迁移困难等问题。awesome-tensorflow-2 正是为了解决这些痛点而生，它通过人工筛选和分类，剔除了过时或低质量的内容，为用户提供了一条清晰的学习路径。无论是官方文档的补充解读，还是针对特定任务（如生成对抗网络 GAN、强化学习 RL、自然语言处理 NLP 及目标检测）的实战项目，这里都能找到对应的优质资源。\n\n这份合集特别适合人工智能领域的开发者、数据科学家、研究人员以及正在从 TensorFlow 1.x 迁移至 2.x 的技术人员。对于初学者，它提供了从基础入门到进阶实战的系统化教程；对于资深从业者，它则是获取最新技术动态、最佳实践代码和深层原理分析的便捷索引。此外，其中还包含部分中文教程资源，对国内用户十分友好。通过利用 awesome-tensorflow-2，用户可以避免在海量信息中盲目搜索，从而将更多精力集中在模型构建与算法创新上，显著提升学习与开发效率。","# Awesome Tensorflow 2 💛 [![Awesome](https:\u002F\u002Fawesome.re\u002Fbadge.svg)](https:\u002F\u002Fawesome.re)\nA curated list of awesome Tensorflow v2 tutorials, blogs, and projects.\n\n![alt text](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_d16a3b402d5f.png)\n\n# 👉 Contents \u003Ca name=\"TOC\" \u002F>👈\n\n\u003C!-- MarkdownTOC depth=4 -->\n* [What are the advantages of TensorFlow v2 ?](#firstSection)\n* [Official Site](#official)\n* [Tutorials](#GitHub-tutorials)\n* [SampleCodes\u002FProjects](#sample)\n    * [General](#GeneralCode)\n    * [Specific Model\u002FTask (like GAN,RL,NLP,...)](#SpecificCode)\n        * [Reinforcement Learning](#RL)\n        * [GAN](#GAN_Code)\n        * [NLP](#NLP_Code)\n        * [Object Detection](#OD)\n        * [Other](#Other_Code)\n* [Videos](#videos)\n    * [TensorFlow World 2019](#TFW19)\n    * [DevSummit 2019](#DevSum)\n    * [Google I\u002FO 2019](#GIO)\n    * [TensorFlow YouTube Channel](#TYC)\n    * [Course](#course)\n    * [Other](#Other_Video)\n* [Blog posts](#blogs)\n* [Other](#other)\n   * [Python wheels](#whls)\n   * [Tools](#tools)\n   * [#PoweredByTF 2.0 Challenge](#PWBYTF2)\n   * [Books](#books)\n\n\u003C!-- \u002FMarkdownTOC -->\n\n\u003Ca name=\"firstSection\" \u002F>\n\n## What are the advantages of TensorFlow v2 ? 👀\n* TensorFlow 2 focuses on simplicity and ease of use, with updates like eager execution, intuitive higher-level APIs, and flexible model   building on any platform\n* There are multiple changes in TensorFlow 2 to make TensorFlow users more productive. TensorFlow 2 removes redundant APIs, makes APIs more consistent (Unified RNNs, Unified Optimizers), and better integrates with the Python runtime with Eager execution.\n\nMore info [here](https:\u002F\u002Fwww.tensorflow.org\u002Ftutorials).\n\nTensorFlow 2.3 is now available! 🎉🎉🎉\n\n![alt text](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_315b02407d17.png)\n\nFor Tensrflow **version \u003C1.x>** see this **[awesome collection](https:\u002F\u002Fgithub.com\u002Fjtoy\u002Fawesome-tensorflow)** created by jtoy.\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_362632fbf7ff.png\" alt=\"down\" width=\"250\" height=\"150\">\n\n\u003Ca name=\"official\" \u002F>\n\n## Official Site 🏢\n* [TensorFlow 2.2](https:\u002F\u002Fwww.tensorflow.org\u002F)\n* [Install](https:\u002F\u002Fwww.tensorflow.org\u002Finstall\u002Fgpu) (Needs CUDA 10.1 & cuDNN = 7.6)\n* [Effective_tf2](https:\u002F\u002Fwww.tensorflow.org\u002Fguide\u002Feffective_tf2)\n* [Quick Start](https:\u002F\u002Fwww.tensorflow.org\u002Ftutorials\u002Fquickstart\u002Fbeginner)\n* [Upgrade guid](https:\u002F\u002Fwww.tensorflow.org\u002Fguide\u002Fupgrade)\n* [Road map](https:\u002F\u002Fwww.tensorflow.org\u002Fcommunity\u002Froadmap)\n* [FAQ](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fcommunity\u002Fblob\u002Fmaster\u002Fsigs\u002Ftesting\u002Ffaq.md)\n* [Blog](https:\u002F\u002Fblog.tensorflow.org\u002F)\n\n[\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_b69833744b2a.png\" alt=\"down\" width=\"30\" height=\"30\">  **Back to Top**](#TOC)\n\n## Tutorials \u003Ca name=\"GitHub-tutorials\" \u002F> 📕 📘 📗 📓\n\n* [TensorFlow Tutorial](https:\u002F\u002Fgithub.com\u002Faymericdamien\u002FTensorFlow-Examples\u002Ftree\u002Fmaster\u002Ftensorflow_v2) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_2bf81d0fa300.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [Official tutorial](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fdocs\u002Ftree\u002Fmaster\u002Fsite\u002Fen\u002Ftutorials) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_2bf81d0fa300.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [Deep Learning with TensorFlow 2 and Keras course](https:\u002F\u002Fgithub.com\u002Fageron\u002Ftf2_course) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_2bf81d0fa300.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [TensorFlow-2.x-Tutorials](https:\u002F\u002Fgithub.com\u002Fdragen1860\u002FTensorFlow-2.x-Tutorials) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_2bf81d0fa300.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [Tensorflow2_tutorials_chinese](https:\u002F\u002Fgithub.com\u002Fczy36mengfei\u002Ftensorflow2_tutorials_chinese) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_ab26d562a07b.png\" alt=\"down\" width=\"50\" height=\"15\">\n* [Tensorflow2.0 tutorial from basic to hard](https:\u002F\u002Fgithub.com\u002FYunYang1994\u002FTensorFlow2.0-Examples) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_ab26d562a07b.png\" alt=\"down\" width=\"50\" height=\"15\">\n* [TensorFlow2.0_Eager_Execution_Tutorials](https:\u002F\u002Fgithub.com\u002Fhellocybernetics\u002FTensorFlow2.0_Eager_Execution_Tutorials) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_339a9cd7d656.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [Tensorflow 2.0 and Keras: what's new, what's shared, what's different](https:\u002F\u002Fgithub.com\u002Fzerotodeeplearning\u002Ftf2_keras) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_ab26d562a07b.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [Practical Exercises in Tensorflow 2.0 for Ian Goodfellows Deep Learning Book](https:\u002F\u002Fgithub.com\u002Fadhiraiyan\u002FDeepLearningWithTF2.0) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_2bf81d0fa300.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [Deep Learning Crash Course-(S9)](https:\u002F\u002Fgithub.com\u002Fisikdogan\u002Fdeep_learning_tutorials) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_339a9cd7d656.png\" alt=\"down\" width=\"50\" height=\"17\">\n\n[\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_b69833744b2a.png\" alt=\"down\" width=\"30\" height=\"30\">  **Back to Top**](#TOC)\n\n## Sample Codes \u002F Projects \u003Ca name=\"sample\" \u002F> ⛏️📐📁\n\n   ### General 🚧 \u003Ca name=\"GeneralCode\" \u002F>\n\n   * [Tensorflow-2.0 Quick Start Guide](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FTensorflow-2.0-Quick-Start-Guide)\n   * [Make Money with Tensorflow 2.0](https:\u002F\u002Fgithub.com\u002FllSourcell\u002FMake_Money_with_Tensorflow_2.0)\n   * [Practical intro to tf2](https:\u002F\u002Fgithub.com\u002Fhimanshurawlani\u002Fpractical_intro_to_tf2)\n   * [Tensorflow2.0 examples](https:\u002F\u002Fgithub.com\u002Fthibo73800\u002Ftensorflow2.0-examples)\n   * [Deep Learning with TensorFlow 2.X (& Keras)](https:\u002F\u002Fgithub.com\u002Fyusugomori\u002Fdeeplearning-tf2)\n   * [TensorFlow 2 Machine Learning Cookbook, published by Packt](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FTensorFlow-2-Machine-Learning-Cookbook)\n   * [Hands On Computer Vision with TensorFlow 2](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FHands-On-Computer-Vision-with-TensorFlow-2)\n   * [Implementing-Deep-Learning-Algorithms-with-TensorFlow-2.0(PacktPub)](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FImplementing-Deep-Learning-Algorithms-with-TensorFlow-2.0)\n   * [Discovering hidden factors of variation in deep networks](https:\u002F\u002Fgithub.com\u002FWarvito\u002Fdiscovering-hidden-factors-of-variation-in-deep-networks)\n   * [Tutorial to run TensorFlow 2 on mobile devices: Android, iOS and Browser](https:\u002F\u002Fgithub.com\u002FEliotAndres\u002Ftensorflow-2-run-on-mobile-devices-ios-android-browser)\n   * [Tensorflow2.x Examples from basic to hard](https:\u002F\u002Fgithub.com\u002FYunYang1994\u002FTensorFlow2.0-Examples)\n   * [Deep-Learning-with-TensorFlow-2.0-in-7-Steps-[Packt]](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FDeep-Learning-with-TensorFlow-2.0-in-7-Steps)\n   * [Getting-Started-with-TensorFlow-2.0-for-Deep-Learning-Video-[Packt]](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FGetting-Started-with-TensorFlow-2.0-for-Deep-Learning-Video)\n   * [TensorFlow 2.0: A Complete Guide on the Brand New TensorFlow - Udemy Course](https:\u002F\u002Fgithub.com\u002Fsergejhorvat\u002FTensorflow2.0_Udemy)\n   * [Interpretability Methods for tf.keras models with Tensorflow 2.0](https:\u002F\u002Fgithub.com\u002Fsicara\u002Ftf-explain)\n   * [AiSpace: Better practices for deep learning model development and deployment For Tensorflow 2.0](https:\u002F\u002Fgithub.com\u002Fyingyuankai\u002FAiSpace)\n   * [Multi-Similarity Loss Re-Implementation in Tensorflow 2.x](https:\u002F\u002Fgithub.com\u002Fshun-lin\u002Fmulti-similarity-loss-tensorflow)\n   * [Deep Learning with TensorFlow 2 and Keras - 2nd Edition PacktPub](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FDeep-Learning-with-TensorFlow-2-and-Keras)\n   * [Graph Neural Networks in TF2 (TensorFlow 2 library implementing Graph Neural Networks by Microsoft)](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftf2-gnn)\n   * [Sarus TF2 Models](https:\u002F\u002Fgithub.com\u002Fsarus-tech\u002Ftf2-published-models) - A long list of recent generative models implemented in clean, easy to reuse, Tensorflow 2 code (Plain Autoencoder, VAE, VQ-VAE, PixelCNN, Gated PixelCNN, PixelCNN++, PixelSNAIL, Conditional Neural Processes).\n   * [TensorFlow 2 in Action by Manning - Code Repository](https:\u002F\u002Fgithub.com\u002Fthushv89\u002Fmanning_tf2_in_action) - Exercises of all the chapters in TensorFlow 2 in Action by Manning\n   * [Activeloop HUB](https:\u002F\u002Fgithub.com\u002Factiveloopai\u002FHub) - The fastest way to store, access & manage datasets with version-control for PyTorch\u002FTensorFlow. Works locally or on any cloud. Scalable data pipelines.\n   * [create-tf-app](https:\u002F\u002Fgithub.com\u002Fradi-cho\u002Fcreate-tf-app) - Project builder command line tool for Tensorflow covering environment management, linting, and logging.\n\n   ### Specific Model\u002FTask (like GAN,RL,NLP,...) \u003Ca name=\"SpecificCode\" \u002F>\n\n   ### Reinforcement Learning \u003Ca name=\"RL\" \u002F>🔮\n   * [Play Super Mario Games using Reinforcement Learning with TensorFlow 2.0](https:\u002F\u002Fgithub.com\u002Fjames94\u002FSuper-Mario-Reinforcement-Learning)\n   * [TensorFlow2.0 Reinforcement Learning Library!(TF2RL)](https:\u002F\u002Fgithub.com\u002Fkeiohta\u002Ftf2rl)\n   * [Scalable and Efficient Deep-RL](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fseed_rl)\n   * [Deep Reinforcement Learning with TensorFlow 2.0](https:\u002F\u002Fgithub.com\u002Finoryy\u002Ftensorflow2-deep-reinforcement-learning)\n   * [Implemented Policy Gradient in Tensorflow2.0](https:\u002F\u002Fgithub.com\u002Fwongongv\u002FPolicyGradient_in_tensorflow2.0)\n   * [TF2 PPO Atari](https:\u002F\u002Fgithub.com\u002FUesugiErii\u002Ftf2-PPO-atari)\n\n   #### GAN \u003Ca name=\"GAN_Code\" \u002F>🌄\n   * [Generative models in Tensorflow 2](https:\u002F\u002Fgithub.com\u002Ftimsainb\u002Ftensorflow2-generative-models\u002F)\n   * [CycleGAN-Tensorflow-2](https:\u002F\u002Fgithub.com\u002FLynnHo\u002FCycleGAN-Tensorflow-2)\n   * [CartoonGAN](https:\u002F\u002Fgithub.com\u002Fmnicnc404\u002FCartoonGan-tensorflow)\n   * [GANs - Tensorflow 2](https:\u002F\u002Fgithub.com\u002FLynnHo\u002FDCGAN-LSGAN-WGAN-GP-DRAGAN-Tensorflow-2)\n   * [Fast-SRGAN (Single Image Super Resolution GAN)](https:\u002F\u002Fgithub.com\u002FHasnainRaz\u002FFast-SRGAN)\n   * [Enhanced Super-Resolution Generative Adversarial Networks](https:\u002F\u002Fgithub.com\u002FpeteryuX\u002Fesrgan-tf2)\n\n   #### NLP \u003Ca name=\"NLP_Code\" \u002F>🌈\n   * [Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch](https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Ftransformers)\n   * [Tensorflow 2 implementation of Causal-BERT](https:\u002F\u002Fgithub.com\u002Fvveitch\u002Fcausal-text-embeddings-tf2)\n   * [Effective NLP in TensorFlow 2](https:\u002F\u002Fgithub.com\u002Fzhedongzheng\u002Ffinch)\n   * [Effective Approaches to Attention-based Neural Machine Translation](https:\u002F\u002Fgithub.com\u002Fthisisiron\u002Fnmt-attention-tf2)\n   * [BERT in TensorFlow 2](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmodels\u002Ftree\u002Fmaster\u002Fofficial\u002Fnlp\u002Fbert)\n   * [A Keras TensorFlow 2.0 implementation of BERT, ALBERT and adapter-BERT](https:\u002F\u002Fgithub.com\u002Fkpe\u002Fbert-for-tf2)\n\n   #### Object Detection \u003Ca name=\"OD\" \u002F>🔥\n   * [MobileNet_V3](https:\u002F\u002Fgithub.com\u002Fcalmisential\u002FMobileNetV3_TensorFlow2.0)\n   * [YOLO v3](https:\u002F\u002Fgithub.com\u002Fzzh8829\u002Fyolov3-tf2)\n   * [Tensorflow Object Detection with Tensorflow 2.0](https:\u002F\u002Fgithub.com\u002FTannerGilbert\u002FTensorflow-Object-Detection-with-Tensorflow-2.0)\n   * [Yolo v4 using TensorFlow 2.x](https:\u002F\u002Fgithub.com\u002FRobotEdh\u002FYolov-4)\n   * [YOLO v3 TensorFlow Lite iOS GPU acceleration](https:\u002F\u002Fgithub.com\u002FJeiKeiLim\u002Ftflite-yolov3-gpu-ready)\n   * [A simple tf.keras implementation of YOLO v4](https:\u002F\u002Fgithub.com\u002Ftaipingeric\u002Fyolo-v4-tf.keras)\n   \n   \n   \n   #### Other \u003Ca name=\"Other_Code\" \u002F>🚦\n   * [A tensorflow2 implementation of some basic CNNs(MobileNetV1\u002FV2\u002FV3, EfficientNet, ResNeXt, InceptionV4, InceptionResNetV1\u002FV2, SENet, SqueezeNet, DenseNet, ShuffleNetV2, ResNet). ](https:\u002F\u002Fgithub.com\u002Fcalmisential\u002FBasic_CNNs_TensorFlow2) \u003C==\n   * [fast and scalable design of risk parity portfolios with TensorFlow 2.0](https:\u002F\u002Fgithub.com\u002Fdppalomar\u002Friskparity.py)\n   * [Tensorflow 2.0 Realtime Multi-Person Pose Estimation](https:\u002F\u002Fgithub.com\u002Fmichalfaber\u002Ftensorflow_Realtime_Multi-Person_Pose_Estimation)\n   * [Train ResNet on ImageNet in Tensorflow 2.0](https:\u002F\u002Fgithub.com\u002FApm5\u002FImageNet_ResNet_Tensorflow2.0)\n   * [CBAM(Convolutional Block Attention Module) implementation on TensowFlow2.0](https:\u002F\u002Fgithub.com\u002Fzhangkaifang\u002FCBAM-TensorFlow2.0)\n   * [ArcFace: Additive Angular Margin Loss for Deep Face Recognition](https:\u002F\u002Fgithub.com\u002FpeteryuX\u002Farcface-tf2)\n   * [Pointnet++ modules implemented as tensorflow 2 keras layers](https:\u002F\u002Fgithub.com\u002Fdgriffiths3\u002Fpointnet2-tensorflow2)\n   * [Edward2 => A lightweight probabilistic programming language in NumPy or TensorFlow](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fedward2)\n   * [Attention OCR in Tensorflow 2.0](https:\u002F\u002Fgithub.com\u002Falleveenstra\u002Fattentionocr)\n   * [An implementation of HTR(Handwritten Text Recognition) using TensorFlow 2.0](https:\u002F\u002Fgithub.com\u002Farthurflor23\u002Fhandwritten-text-recognition)\n   * [Some state-of-the-art Few Shot Learning algorithms in Tensorflow 2](https:\u002F\u002Fgithub.com\u002FClementWalter\u002FKeras-FewShotLearning)\n   * [Tensorflow2 question-answering (Kaggle)](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Ftensorflow2-question-answering\u002Fnotebooks)\n   * [Tensorflow 2.0 example](https:\u002F\u002Fgithub.com\u002FApm5\u002Ftensorflow_2.0_example)\n   * [Single pose estimation for iOS and android using TensorFlow 2.0](https:\u002F\u002Fgithub.com\u002Ftucan9389\u002Ftf2-mobile-pose-estimation)\n   * [Speech Recognition](https:\u002F\u002Fgithub.com\u002Fmszulc913\u002Fspeechrecognitionchalange-lstm-tensorflow2)\n   * [Music transformer](https:\u002F\u002Fgithub.com\u002Fjason9693\u002FMusicTransformer-tensorflow2.0)\n   * [Handwritten Text Recognition (HTR) system implemented using TensorFlow 2.0](https:\u002F\u002Fgithub.com\u002Farthurflor23\u002Fhandwritten-text-recognition)\n   * [Meta learning framework with Tensorflow 2.0](https:\u002F\u002Fgithub.com\u002Fsiavash-khodadadeh\u002FMetaLearning-TF2.0)\n   * [Simple Template for Tensorflow 2.X](https:\u002F\u002Fgithub.com\u002FSCP-173-cool\u002FTF2_template)\n   * [Shortest_triplet_network_with_TF2.0](https:\u002F\u002Fgithub.com\u002FFraLupo\u002Fshortest_triplet_network_with_tf2.0)\n   * [Arbitrary Style Transfer in Real-time](https:\u002F\u002Fgithub.com\u002Fgs18113\u002FAdaIN-TensorFlow2)\n   * [RetinaFace: Single-stage Dense Face Localisation in the Wild](https:\u002F\u002Fgithub.com\u002FpeteryuX\u002Fretinaface-tf2)\n   * [PC-DARTS: Partial Channel Connections for Memory-Efficient Differentiable Architecture Search](https:\u002F\u002Fgithub.com\u002FpeteryuX\u002Fpcdarts-tf2)\n   * [An implementation of model-predictive control algorithms using TensorFlow 2](https:\u002F\u002Fgithub.com\u002Fthiagopbueno\u002Ftf-mpc)\n   * [TensorflowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2](https:\u002F\u002Fgithub.com\u002Fdathudeptrai\u002FTensorflowTTS)\n\n[\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_b69833744b2a.png\" alt=\"down\" width=\"30\" height=\"30\">  **Back to Top**](#TOC)\n\n## Videos  🎥 📺 📹      \u003Ca name=\"videos\" \u002F>\n### TensorFlow World 2019 \u003Ca name=\"TFW19\" \u002F>\n   * [PlayList](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvxcmHHRftsuiO1GyinVAwUg)\n   * [Introduction to TensorFlow 2.0: Easier for beginners, and more powerful for experts](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=5ECD8J3dvDQ&list=PLQY2H8rRoyvxcmHHRftsuiO1GyinVAwUg&index=4&t=0s)\n\n### DevSummit \u003Ca name=\"DevSum\" \u002F>\n   * [PlayList 2019](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvzoUYI26kHmKSJBedn3SQuB)\n   * [**Introducing TensorFlow 2.0 and its high-level APIs (TF Dev Summit '19)**](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=k5c-vg4rjBw)\n   * [PlayList 2020](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvzuJw20FG82Lgm2SZjTdIXU)\n   \n### Google I\u002FO \u003Ca name=\"GIO\" \u002F>\n   * [PlayList](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLOU2XLYxmsILVTiOlMJdo7RQS55jYhsMi)\n   * [**Getting Started with TensorFlow 2.0 (Google I\u002FO'19)**](https:\u002F\u002Fwww.youtube.com\u002Fwatch?reload=9&v=lEljKc9ZtU8)\n\n### TensorFlow YouTube Channel \u003Ca name=\"TYC\" \u002F>\n   * [Channel](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUC0rqucBdTuFTjJiefW5t-IQ)\n   * [Coding TensorFlow](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvwLbzbnKJ59NkZvQAW9wLbx)\n   * [#AskTensorFlow](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvypL1nu_65Uhf5LuWlZdmSL)\n   * [TensorFlow Meets](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvyOeER8UNF-1zXaCKGLZVog)\n   * [Machine Learning Foundations](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLOU2XLYxmsII9mzQ-Xxug4l2o04JBrkLV)\n   * [Powered by TensorFlow](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvyLQDomfBj-ptdBGTxAHwV_)\n   * [Natural Language Processing](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=fNxaJsNG3-s&list=PLQY2H8rRoyvzDbLUZkbudP-MFQZwNmU4S)\n   * [Inside TensorFlow](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvzIuB8rZXs7pfyjiSUs8Vza)\n   \n### Course  \u003Ca name=\"course\" \u002F>\n   * [TensorFlow 2.0 Full Tutorial - Python Neural Networks for Beginners](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=6g4O5UOH304)\n   * [Learning TensorFlow 2.0 (Udemy)](https:\u002F\u002Fwww.udemy.com\u002Flearning-tensorflow-20\u002F)\n   * [TensorFlow in Practice Specialization](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Ftensorflow-in-practice)\n\n### Other   \u003Ca name=\"Other_Video\" \u002F>\n   * [GTC Silicon Valley-2019 ID:S9495:An Introduction to TensorFlow 2.0](https:\u002F\u002Fdeveloper.nvidia.com\u002Fgtc\u002F2019\u002Fvideo\u002FS9495)\n   * [Make Money withTensorflow 2.0](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=WS9Nckd2kq0)\n\n [\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_b69833744b2a.png\" alt=\"down\" width=\"30\" height=\"30\">  **Back to Top**](#TOC)\n\n## Blog posts \u003Ca name=\"blogs\" \u002F>📃\n* [Tensorflow-2-models-migration-and-new-design](https:\u002F\u002Fpgaleone.eu\u002Ftensorflow\u002Fgan\u002F2018\u002F11\u002F04\u002Ftensorflow-2-models-migration-and-new-design\u002F)\n* [Standardizing on Keras: Guidance on High-level APIs in TensorFlow 2.0](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fstandardizing-on-keras-guidance-on-high-level-apis-in-tensorflow-2-0-bad2b04c819a)\n* [Test Drive TensorFlow 2.0 Alpha](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Ftest-drive-tensorflow-2-0-alpha-b6dd1e522b01)\n* [Recap of the 2019 TensorFlow Dev Summit](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Frecap-of-the-2019-tensorflow-dev-summit-1b5ede42da8d)\n* [Upgrading your code to TensorFlow 2.0](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fupgrading-your-code-to-tensorflow-2-0-f72c3a4d83b5)\n* [Effective TensorFlow 2.0: Best Practices and What’s Changed](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Feffective-tensorflow-2-0-best-practices-and-whats-changed-a0ca48767aff)\n* [What are Symbolic and Imperative APIs in TensorFlow 2.0?](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fwhat-are-symbolic-and-imperative-apis-in-tensorflow-2-0-dfccecb01021)\n* [What’s coming in TensorFlow 2.0](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fwhats-coming-in-tensorflow-2-0-d3663832e9b8)\n* [My Notes on TensorFlow 2.0](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Ftesting-for-tensorflow-2-0-2db0d17c37f0)\n* [Create The Transformer With Tensorflow 2.0](https:\u002F\u002Fmachinetalk.org\u002F2019\u002F04\u002F29\u002Fcreate-the-transformer-with-tensorflow-2-0\u002F)\n* [Fast-SCNN explained and implemented using Tensorflow 2.0](https:\u002F\u002Fmedium.com\u002Fdeep-learning-journals\u002Ffast-scnn-explained-and-implemented-using-tensorflow-2-0-6bd17c17a49e)\n* [Image Classification with high-level API of Tensorflow 2.0](https:\u002F\u002Fhackernoon.com\u002Fimage-classification-with-tensorflow-2-0-d5a98bcffce1)\n* [A Transformer Chatbot Tutorial with TensorFlow 2.0](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fa-transformer-chatbot-tutorial-with-tensorflow-2-0-88bf59e66fe2)\n* [Easy Image Classification with TensorFlow 2.0](https:\u002F\u002Ftowardsdatascience.com\u002Feasy-image-classification-with-tensorflow-2-0-f734fee52d13)\n* [Implementing an Autoencoder in TensorFlow 2.0](https:\u002F\u002Fmedium.com\u002F@abien.agarap\u002Fimplementing-an-autoencoder-in-tensorflow-2-0-5e86126e9f7)\n* [How to build a wide-and-deep model using Keras in TensorFlow](https:\u002F\u002Ftowardsdatascience.com\u002Fhow-to-build-a-wide-and-deep-model-using-keras-in-tensorflow-2-0-2f7a236b5a4b)\n* [Heart Disease Prediction in TensorFlow 2](https:\u002F\u002Fmedium.com\u002F@curiousily\u002Fheart-disease-prediction-in-tensorflow-2-tensorflow-for-hackers-part-ii-378eef0400ee)\n* [Generating Text with TensorFlow 2.0](https:\u002F\u002Ftowardsdatascience.com\u002Fgenerating-text-with-tensorflow-2-0-6a65c7bdc568)\n* [Ten Important Updates from TensorFlow 2.0](https:\u002F\u002Fwww.datacamp.com\u002Fcommunity\u002Ftutorials\u002Ften-important-updates-tensorflow)\n* [TensorFlow 2.0 Global Docs Sprint Cheatsheet](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fhttps-medium-com-margaretmz-tf-docs-sprint-cheatsheet-7cb1dfd3e8b5)\n* [Announcing the winners of the #PoweredByTF 2.0 Dev Post Challenge](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fannouncing-the-winners-of-the-poweredbytf-2-0-dev-post-challenge-af39d9d5a208)\n* [Analyzing tf.function to discover AutoGraph strengths and subtleties](https:\u002F\u002Fpgaleone.eu\u002Ftensorflow\u002Ftf.function\u002F2019\u002F03\u002F21\u002Fdissecting-tf-function-part-1\u002F)\n* [Information Theory with Tensorflow 2.0](https:\u002F\u002Fdev.to\u002Fmmithrakumar\u002Finformation-theory-with-tensorflow-2-0-29ao)\n* [Portable Computer Vision: TensorFlow 2.0 on a Raspberry Pi](https:\u002F\u002Ftowardsdatascience.com\u002Fportable-computer-vision-tensorflow-2-0-on-a-raspberry-pi-part-1-of-2-84e318798ce9)\n* [From Tensorflow 1.0 to PyTorch & back to Tensorflow 2.0](https:\u002F\u002Ftowardsdatascience.com\u002Ffrom-tensorflow-1-0-to-pytorch-back-to-tensorflow-2-0-f2f8a4c716b7)\n* [Hugging Face: State-of-the-Art Natural Language Processing in ten lines of TensorFlow 2.0](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fusing-tensorflow-2-for-state-of-the-art-natural-language-processing-102445cda54a)\n-----------------------------------------------------------------------------------------------------------------------\n* [TensorFlow 2.0 Alpha : Let seek the New in the Old](https:\u002F\u002Fcv-tricks.com\u002Ftensorflow-tutorial\u002Ftensorflow-2-0-alpha\u002F)\n* [Announcing TensorFlow 2.0 Beta](https:\u002F\u002Fwww.datacamp.com\u002Fcommunity\u002Ftutorials\u002Ften-important-updates-tensorflow)\n* [TensorFlow 2.0 is now available!](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Ftensorflow-2-0-is-now-available-57d706c2a9ab)\n\n\n[\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_b69833744b2a.png\" alt=\"down\" width=\"30\" height=\"30\">  **Back to Top**](#TOC)\n\n## Other \u003Ca name=\"other\" \u002F>🌱\n### Python wheels  \u003Ca name=\"whls\" \u002F>🐍\n* [Tensorflow 2.1.0 Linux GPU (Compute 7.0, 7.2, 7.5), Python 3.8, CUDA 10.2, cuDNN 7.6, AVX2, MKL, TensorRT 6](https:\u002F\u002Fgithub.com\u002Fyaroslavvb\u002Ftensorflow-community-wheels\u002Fissues\u002F140)\n* [TensorFlow 2.0.0, Python 3.7, Docker Image, no AVX \u002F Nehalem-CPU-Instructionset | Linux x86_64](https:\u002F\u002Fgithub.com\u002Fyaroslavvb\u002Ftensorflow-community-wheels\u002Fissues\u002F125)\n* [Tensorflow v2.0.0, Python 3.7, CUDA 10.0, cuDNN 7.6.4, without AVX, Windows 10 x64](https:\u002F\u002Fgithub.com\u002Fyaroslavvb\u002Ftensorflow-community-wheels\u002Fissues\u002F127)\n* [TensorFlow 2.0, GPU (Compute Compatible 6.1,7.5) , CUDA 10.1, cuDNN 7.6, AVX, Python 3.6, MKL, XLA, CPU i3-8100, Ubuntu 18.04](https:\u002F\u002Fgithub.com\u002Fyaroslavvb\u002Ftensorflow-community-wheels\u002Fissues\u002F129)\n\n### Tools \u003Ca name=\"tools\" \u002F>🔧\n* [TensorFlow 2.0 upgrader service](https:\u002F\u002Fgithub.com\u002Flc0\u002Ftf2up)\n* [Tensorflow Hub](https:\u002F\u002Ftfhub.dev\u002Fs?q=tf2)\n* [Guild AI](https:\u002F\u002Fguild.ai)\n\n### #PoweredByTF 2.0 Challenge\u003Ca name=\"PWBYTF2\" \u002F> 🔫 💣 🏆\n\n* [HomePage](https:\u002F\u002Ftensorflow.devpost.com\u002F)\n* [Submissions](https:\u002F\u002Ftensorflow.devpost.com\u002Fsubmissions)\n\n### Books \u003Ca name=\"books\" \u002F>📚\n\n* [TensorFlow 2.0 Quick Start Guide](https:\u002F\u002Fwww.packtpub.com\u002Fbig-data-and-business-intelligence\u002Ftensorflow-20-quick-start-guide)\n* [Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition](https:\u002F\u002Fwww.oreilly.com\u002Flibrary\u002Fview\u002Fhands-on-machine-learning\u002F9781492032632\u002F)\n* [TensorFlow Machine Learning Cookbook - Second Edition](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fannouncing-tensorflow-2-0-beta-abb24bbfbe3d)\n* [Tensorflow 2 in Action](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Ftensorflow-in-action)\n\n[\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_b69833744b2a.png\" alt=\"down\" width=\"30\" height=\"30\">  **Back to Top**](#TOC)\n\n## Contributions 📭  \u003Ca name=\"contributions\" \u002F>\n\nYour contributions are always welcome!\n\nIf you want to contribute to this list (please do), send me a pull request\nAlso, if you notice that any of the above listed repositories should be deprecated, due to any of the following reasons:\n\n* Repository's owner explicitly say that \"this library is not maintained\".\n* Not committed for long time (2~3 years).\n\nMore info on the [guidelines](https:\u002F\u002Fgithub.com\u002FAmin-Tgz\u002FAwesome-TensorFlow-2\u002Fblob\u002Fmaster\u002Fcontributing.md)\n\n## License\nLicensed under the [Creative Commons CC0 License](https:\u002F\u002Fcreativecommons.org\u002Fpublicdomain\u002Fzero\u002F1.0\u002F).\n","# 令人惊叹的 TensorFlow 2 💛 [![Awesome](https:\u002F\u002Fawesome.re\u002Fbadge.svg)](https:\u002F\u002Fawesome.re)\n一份精心整理的、关于 TensorFlow v2 的优秀教程、博客和项目的列表。\n\n![alt text](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_d16a3b402d5f.png)\n\n# 👉 目录 \u003Ca name=\"TOC\" \u002F>👈\n\n\u003C!-- MarkdownTOC depth=4 -->\n* [TensorFlow v2 有哪些优势？](#firstSection)\n* [官方网站](#official)\n* [教程](#GitHub-tutorials)\n* [示例代码\u002F项目](#sample)\n    * [通用](#GeneralCode)\n    * [特定模型\u002F任务（如 GAN、RL、NLP 等）](#SpecificCode)\n        * [强化学习](#RL)\n        * [GAN](#GAN_Code)\n        * [NLP](#NLP_Code)\n        * [目标检测](#OD)\n        * [其他](#Other_Code)\n* [视频](#videos)\n    * [TensorFlow World 2019](#TFW19)\n    * [DevSummit 2019](#DevSum)\n    * [Google I\u002FO 2019](#GIO)\n    * [TensorFlow YouTube 频道](#TYC)\n    * [课程](#course)\n    * [其他](#Other_Video)\n* [博客文章](#blogs)\n* [其他](#other)\n   * [Python wheels](#whls)\n   * [工具](#tools)\n   * [#PoweredByTF 2.0 挑战赛](#PWBYTF2)\n   * [书籍](#books)\n\n\u003C!-- \u002FMarkdownTOC -->\n\n\u003Ca name=\"firstSection\" \u002F>\n\n## TensorFlow v2 有哪些优势？👀\n* TensorFlow 2 专注于简洁性和易用性，引入了诸如急切执行、直观的高层 API 以及在任何平台上灵活构建模型等更新。\n* TensorFlow 2 进行了多项改进，以提高 TensorFlow 用户的工作效率。它移除了冗余的 API，使 API 更加一致（统一 RNN 和优化器），并通过急切执行更好地与 Python 运行时集成。\n\n更多信息请参见 [这里](https:\u002F\u002Fwww.tensorflow.org\u002Ftutorials)。\n\nTensorFlow 2.3 现已发布！🎉🎉🎉\n\n![alt text](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_315b02407d17.png)\n\n对于 TensorFlow **\u003C1.x 版本**，请参阅由 jtoy 创建的这个 **[精彩合集](https:\u002F\u002Fgithub.com\u002Fjtoy\u002Fawesome-tensorflow)**。\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_362632fbf7ff.png\" alt=\"down\" width=\"250\" height=\"150\">\n\n\u003Ca name=\"official\" \u002F>\n\n## 官方网站 🏢\n* [TensorFlow 2.2](https:\u002F\u002Fwww.tensorflow.org\u002F)\n* [安装指南](https:\u002F\u002Fwww.tensorflow.org\u002Finstall\u002Fgpu)（需要 CUDA 10.1 和 cuDNN = 7.6）\n* [Effective_tf2](https:\u002F\u002Fwww.tensorflow.org\u002Fguide\u002Feffective_tf2)\n* [快速入门](https:\u002F\u002Fwww.tensorflow.org\u002Ftutorials\u002Fquickstart\u002Fbeginner)\n* [升级指南](https:\u002F\u002Fwww.tensorflow.org\u002Fguide\u002Fupgrade)\n* [路线图](https:\u002F\u002Fwww.tensorflow.org\u002Fcommunity\u002Froadmap)\n* [常见问题解答](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fcommunity\u002Fblob\u002Fmaster\u002Fsigs\u002Ftesting\u002Ffaq.md)\n* [博客](https:\u002F\u002Fblog.tensorflow.org\u002F)\n\n[\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_b69833744b2a.png\" alt=\"down\" width=\"30\" height=\"30\">  **返回顶部**](#TOC)\n\n## 教程 \u003Ca name=\"GitHub-tutorials\" \u002F> 📕 📘 📗 📓\n\n* [TensorFlow 教程](https:\u002F\u002Fgithub.com\u002Faymericdamien\u002FTensorFlow-Examples\u002Ftree\u002Fmaster\u002Ftensorflow_v2) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_2bf81d0fa300.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [官方教程](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fdocs\u002Ftree\u002Fmaster\u002Fsite\u002Fen\u002Ftutorials) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_2bf81d0fa300.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [使用 TensorFlow 2 和 Keras 的深度学习课程](https:\u002F\u002Fgithub.com\u002Fageron\u002Ftf2_course) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_2bf81d0fa300.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [TensorFlow-2.x-Tutorials](https:\u002F\u002Fgithub.com\u002Fdragen1860\u002FTensorFlow-2.x-Tutorials) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_2bf81d0fa300.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [Tensorflow2_tutorials_chinese](https:\u002F\u002Fgithub.com\u002Fczy36mengfei\u002Ftensorflow2_tutorials_chinese) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_ab26d562a07b.png\" alt=\"down\" width=\"50\" height=\"15\">\n* [从基础到高级的 TensorFlow2.0 教程](https:\u002F\u002Fgithub.com\u002FYunYang1994\u002FTensorFlow2.0-Examples) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_ab26d562a07b.png\" alt=\"down\" width=\"50\" height=\"15\">\n* [TensorFlow2.0_Eager_Execution_Tutorials](https:\u002F\u002Fgithub.com\u002Fhellocybernetics\u002FTensorFlow2.0_Eager_Execution_Tutorials) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_339a9cd7d656.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [TensorFlow 2.0 和 Keras：新特性、共性与差异](https:\u002F\u002Fgithub.com\u002Fzerotodeeplearning\u002Ftf2_keras) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_ab26d562a07b.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [针对 Ian Goodfellow 深度学习书籍的 TensorFlow 2.0 实践练习](https:\u002F\u002Fgithub.com\u002Fadhiraiyan\u002FDeepLearningWithTF2.0) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_2bf81d0fa300.png\" alt=\"down\" width=\"50\" height=\"17\">\n* [深度学习速成课程-(S9)](https:\u002F\u002Fgithub.com\u002Fisikdogan\u002Fdeep_learning_tutorials) \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_339a9cd7d656.png\" alt=\"down\" width=\"50\" height=\"17\">\n\n[\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_b69833744b2a.png\" alt=\"down\" width=\"30\" height=\"30\">  **返回顶部**](#TOC)\n\n## 示例代码 \u002F 项目 \u003Ca name=\"sample\" \u002F> ⛏️📐📁\n\n   ### 通用 🚧 \u003Ca name=\"GeneralCode\" \u002F>\n\n* [TensorFlow 2.0 快速入门指南](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FTensorflow-2.0-Quick-Start-Guide)\n   * [用 TensorFlow 2.0 赚钱](https:\u002F\u002Fgithub.com\u002FllSourcell\u002FMake_Money_with_Tensorflow_2.0)\n   * [tf2 实用入门](https:\u002F\u002Fgithub.com\u002Fhimanshurawlani\u002Fpractical_intro_to_tf2)\n   * [TensorFlow 2.0 示例](https:\u002F\u002Fgithub.com\u002Fthibo73800\u002Ftensorflow2.0-examples)\n   * [使用 TensorFlow 2.X（及 Keras）进行深度学习](https:\u002F\u002Fgithub.com\u002Fyusugomori\u002Fdeeplearning-tf2)\n   * [由 Packt 出版的 TensorFlow 2 机器学习 Cookbook](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FTensorFlow-2-Machine-Learning-Cookbook)\n   * [动手实践：使用 TensorFlow 2 的计算机视觉](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FHands-On-Computer-Vision-with-TensorFlow-2)\n   * [使用 TensorFlow 2.0 实现深度学习算法（PacktPub）](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FImplementing-Deep-Learning-Algorithms-with-TensorFlow-2.0)\n   * [发现深度网络中的隐藏变化因子](https:\u002F\u002Fgithub.com\u002FWarvito\u002Fdiscovering-hidden-factors-of-variation-in-deep-networks)\n   * [在移动设备上运行 TensorFlow 2 的教程：Android、iOS 和浏览器](https:\u002F\u002Fgithub.com\u002FEliotAndres\u002Ftensorflow-2-run-on-mobile-devices-ios-android-browser)\n   * [从基础到高级的 TensorFlow 2.x 示例](https:\u002F\u002Fgithub.com\u002FYunYang1994\u002FTensorFlow2.0-Examples)\n   * [7 步掌握 TensorFlow 2.0 深度学习（Packt）](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FDeep-Learning-with-TensorFlow-2.0-in-7-Steps)\n   * [深度学习入门视频：TensorFlow 2.0](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FGetting-Started-with-TensorFlow-2.0-for-Deep-Learning-Video)\n   * [TensorFlow 2.0：全新 TensorFlow 完全指南——Udemy 课程](https:\u002F\u002Fgithub.com\u002Fsergejhorvat\u002FTensorflow2.0_Udemy)\n   * [使用 TensorFlow 2.0 对 tf.keras 模型的可解释性方法](https:\u002F\u002Fgithub.com\u002Fsicara\u002Ftf-explain)\n   * [AiSpace：针对 TensorFlow 2.0 的深度学习模型开发与部署最佳实践](https:\u002F\u002Fgithub.com\u002Fyingyuankai\u002FAiSpace)\n   * [在 TensorFlow 2.x 中重新实现多相似性损失](https:\u002F\u002Fgithub.com\u002Fshun-lin\u002Fmulti-similarity-loss-tensorflow)\n   * [使用 TensorFlow 2 和 Keras 进行深度学习——第 2 版 PacktPub](https:\u002F\u002Fgithub.com\u002FPacktPublishing\u002FDeep-Learning-with-TensorFlow-2-and-Keras)\n   * [TF2 中的图神经网络（微软实现的图神经网络 TensorFlow 2 库）](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftf2-gnn)\n   * [Sarus TF2 模型](https:\u002F\u002Fgithub.com\u002Fsarus-tech\u002Ftf2-published-models)——一系列近期生成模型，采用简洁易复用的 TensorFlow 2 代码实现（普通自编码器、VAE、VQ-VAE、PixelCNN、门控 PixelCNN、PixelCNN++、PixelSNAIL、条件神经过程）。\n   * [Manning 出版的《TensorFlow 2 in Action》代码仓库](https:\u002F\u002Fgithub.com\u002Fthushv89\u002Fmanning_tf2_in_action)——涵盖 Manning 出版的《TensorFlow 2 in Action》各章节的所有练习。\n   * [Activeloop HUB](https:\u002F\u002Fgithub.com\u002Factiveloopai\u002FHub)——以版本控制方式存储、访问和管理 PyTorch\u002FTensorFlow 数据集的最快途径。支持本地或任何云端环境，可扩展的数据流水线。\n   * [create-tf-app](https:\u002F\u002Fgithub.com\u002Fradi-cho\u002Fcreate-tf-app)——一个用于 TensorFlow 的项目构建命令行工具，涵盖环境管理、代码检查和日志记录。\n\n   ### 特定模型\u002F任务（如 GAN、RL、NLP 等） \u003Ca name=\"SpecificCode\" \u002F>\n\n   ### 强化学习 \u003Ca name=\"RL\" \u002F>🔮\n   * [使用强化学习和 TensorFlow 2.0 玩超级马里奥游戏](https:\u002F\u002Fgithub.com\u002Fjames94\u002FSuper-Mario-Reinforcement-Learning)\n   * [TensorFlow 2.0 强化学习库！（TF2RL）](https:\u002F\u002Fgithub.com\u002Fkeiohta\u002Ftf2rl)\n   * [可扩展且高效的深度强化学习](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fseed_rl)\n   * [使用 TensorFlow 2.0 进行深度强化学习](https:\u002F\u002Fgithub.com\u002Finoryy\u002Ftensorflow2-deep-reinforcement-learning)\n   * [在 TensorFlow 2.0 中实现策略梯度](https:\u002F\u002Fgithub.com\u002Fwongongv\u002FPolicyGradient_in_tensorflow2.0)\n   * [TF2 PPO Atari](https:\u002F\u002Fgithub.com\u002FUesugiErii\u002Ftf2-PPO-atari)\n\n   #### GAN \u003Ca name=\"GAN_Code\" \u002F>🌄\n   * [TensorFlow 2 中的生成模型](https:\u002F\u002Fgithub.com\u002Ftimsainb\u002Ftensorflow2-generative-models\u002F)\n   * [CycleGAN-TensorFlow-2](https:\u002F\u002Fgithub.com\u002FLynnHo\u002FCycleGAN-Tensorflow-2)\n   * [CartoonGAN](https:\u002F\u002Fgithub.com\u002Fmnicnc404\u002FCartoonGan-tensorflow)\n   * [GANs - TensorFlow 2](https:\u002F\u002Fgithub.com\u002FLynnHo\u002FDCGAN-LSGAN-WGAN-GP-DRAGAN-Tensorflow-2)\n   * [快速 SRGAN（单张图像超分辨率 GAN）](https:\u002F\u002Fgithub.com\u002FHasnainRaz\u002FFast-SRGAN)\n   * [增强型超分辨率生成对抗网络](https:\u002F\u002Fgithub.com\u002FpeteryuX\u002Fesrgan-tf2)\n\n   #### NLP \u003Ca name=\"NLP_Code\" \u002F>🌈\n   * [Transformers：面向 TensorFlow 2.0 和 PyTorch 的最先进自然语言处理框架](https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Ftransformers)\n   * [因果 BERT 的 TensorFlow 2 实现](https:\u002F\u002Fgithub.com\u002Fvveitch\u002Fcausal-text-embeddings-tf2)\n   * [在 TensorFlow 2 中高效进行 NLP](https:\u002F\u002Fgithub.com\u002Fzhedongzheng\u002Ffinch)\n   * [基于注意力机制的神经机器翻译的有效方法](https:\u002F\u002Fgithub.com\u002Fthisisiron\u002Fnmt-attention-tf2)\n   * [BERT 在 TensorFlow 2 中的实现](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmodels\u002Ftree\u002Fmaster\u002Fofficial\u002Fnlp\u002Fbert)\n   * [BERT、ALBERT 和适配器 BERT 的 Keras TensorFlow 2.0 实现](https:\u002F\u002Fgithub.com\u002Fkpe\u002Fbert-for-tf2)\n\n#### 目标检测 \u003Ca name=\"OD\" \u002F>🔥\n   * [MobileNet_V3](https:\u002F\u002Fgithub.com\u002Fcalmisential\u002FMobileNetV3_TensorFlow2.0)\n   * [YOLO v3](https:\u002F\u002Fgithub.com\u002Fzzh8829\u002Fyolov3-tf2)\n   * [Tensorflow Object Detection with Tensorflow 2.0](https:\u002F\u002Fgithub.com\u002FTannerGilbert\u002FTensorflow-Object-Detection-with-Tensorflow-2.0)\n   * [Yolo v4 using TensorFlow 2.x](https:\u002F\u002Fgithub.com\u002FRobotEdh\u002FYolov-4)\n   * [YOLO v3 TensorFlow Lite iOS GPU acceleration](https:\u002F\u002Fgithub.com\u002FJeiKeiLim\u002Ftflite-yolov3-gpu-ready)\n   * [A simple tf.keras implementation of YOLO v4](https:\u002F\u002Fgithub.com\u002Ftaipingeric\u002Fyolo-v4-tf.keras)\n   \n   \n   \n   #### 其他 \u003Ca name=\"Other_Code\" \u002F>🚦\n   * [A tensorflow2 implementation of some basic CNNs(MobileNetV1\u002FV2\u002FV3, EfficientNet, ResNeXt, InceptionV4, InceptionResNetV1\u002FV2, SENet, SqueezeNet, DenseNet, ShuffleNetV2, ResNet). ](https:\u002F\u002Fgithub.com\u002Fcalmisential\u002FBasic_CNNs_TensorFlow2) \u003C==\n   * [fast and scalable design of risk parity portfolios with TensorFlow 2.0](https:\u002F\u002Fgithub.com\u002Fdppalomar\u002Friskparity.py)\n   * [Tensorflow 2.0 Realtime Multi-Person Pose Estimation](https:\u002F\u002Fgithub.com\u002Fmichalfaber\u002Ftensorflow_Realtime_Multi-Person_Pose_Estimation)\n   * [Train ResNet on ImageNet in Tensorflow 2.0](https:\u002F\u002Fgithub.com\u002FApm5\u002FImageNet_ResNet_Tensorflow2.0)\n   * [CBAM(Convolutional Block Attention Module) implementation on TensowFlow2.0](https:\u002F\u002Fgithub.com\u002Fzhangkaifang\u002FCBAM-TensorFlow2.0)\n   * [ArcFace: Additive Angular Margin Loss for Deep Face Recognition](https:\u002F\u002Fgithub.com\u002FpeteryuX\u002Farcface-tf2)\n   * [Pointnet++ modules implemented as tensorflow 2 keras layers](https:\u002F\u002Fgithub.com\u002Fdgriffiths3\u002Fpointnet2-tensorflow2)\n   * [Edward2 => A lightweight probabilistic programming language in NumPy or TensorFlow](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fedward2)\n   * [Attention OCR in Tensorflow 2.0](https:\u002F\u002Fgithub.com\u002Falleveenstra\u002Fattentionocr)\n   * [An implementation of HTR(Handwritten Text Recognition) using TensorFlow 2.0](https:\u002F\u002Fgithub.com\u002Farthurflor23\u002Fhandwritten-text-recognition)\n   * [Some state-of-the-art Few Shot Learning algorithms in Tensorflow 2](https:\u002F\u002Fgithub.com\u002FClementWalter\u002FKeras-FewShotLearning)\n   * [Tensorflow2 question-answering (Kaggle)](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Ftensorflow2-question-answering\u002Fnotebooks)\n   * [Tensorflow 2.0 example](https:\u002F\u002Fgithub.com\u002FApm5\u002Ftensorflow_2.0_example)\n   * [Single pose estimation for iOS and android using TensorFlow 2.0](https:\u002F\u002Fgithub.com\u002Ftucan9389\u002Ftf2-mobile-pose-estimation)\n   * [Speech Recognition](https:\u002F\u002Fgithub.com\u002Fmszulc913\u002Fspeechrecognitionchalange-lstm-tensorflow2)\n   * [Music transformer](https:\u002F\u002Fgithub.com\u002Fjason9693\u002FMusicTransformer-tensorflow2.0)\n   * [Handwritten Text Recognition (HTR) system implemented using TensorFlow 2.0](https:\u002F\u002Fgithub.com\u002Farthurflor23\u002Fhandwritten-text-recognition)\n   * [Meta learning framework with Tensorflow 2.0](https:\u002F\u002Fgithub.com\u002Fsiavash-khodadadeh\u002FMetaLearning-TF2.0)\n   * [Simple Template for Tensorflow 2.X](https:\u002F\u002Fgithub.com\u002FSCP-173-cool\u002FTF2_template)\n   * [Shortest_triplet_network_with_TF2.0](https:\u002F\u002Fgithub.com\u002FFraLupo\u002Fshortest_triplet_network_with_tf2.0)\n   * [Arbitrary Style Transfer in Real-time](https:\u002F\u002Fgithub.com\u002Fgs18113\u002FAdaIN-TensorFlow2)\n   * [RetinaFace: Single-stage Dense Face Localisation in the Wild](https:\u002F\u002Fgithub.com\u002FpeteryuX\u002Fretinaface-tf2)\n   * [PC-DARTS: Partial Channel Connections for Memory-Efficient Differentiable Architecture Search](https:\u002F\u002Fgithub.com\u002FpeteryuX\u002Fpcdarts-tf2)\n   * [An implementation of model-predictive control algorithms using TensorFlow 2](https:\u002F\u002Fgithub.com\u002Fthiagopbueno\u002Ftf-mpc)\n   * [TensorflowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2](https:\u002F\u002Fgithub.com\u002Fdathudeptrai\u002FTensorflowTTS)\n\n[\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_b69833744b2a.png\" alt=\"down\" width=\"30\" height=\"30\">  **回到顶部**](#TOC)\n\n\n\n## 视频  🎥 📺 📹      \u003Ca name=\"videos\" \u002F>\n### TensorFlow World 2019 \u003Ca name=\"TFW19\" \u002F>\n   * [播放列表](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvxcmHHRftsuiO1GyinVAwUg)\n   * [TensorFlow 2.0简介：对初学者更友好，对专家更强大](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=5ECD8J3dvDQ&list=PLQY2H8rRoyvxcmHHRftsuiO1GyinVAwUg&index=4&t=0s)\n\n### DevSummit \u003Ca name=\"DevSum\" \u002F>\n   * [2019年播放列表](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvzoUYI26kHmKSJBedn3SQuB)\n   * [**介绍TensorFlow 2.0及其高级API（TF Dev Summit '19）**](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=k5c-vg4rjBw)\n   * [2020年播放列表](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvzuJw20FG82Lgm2SZjTdIXU)\n   \n### Google I\u002FO \u003Ca name=\"GIO\" \u002F>\n   * [播放列表](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLOU2XLYxmsILVTiOlMJdo7RQS55jYhsMi)\n   * [**TensorFlow 2.0入门（Google I\u002FO'19）**](https:\u002F\u002Fwww.youtube.com\u002Fwatch?reload=9&v=lEljKc9ZtU8)\n\n### TensorFlow YouTube频道 \u003Ca name=\"TYC\" \u002F>\n   * [频道](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUC0rqucBdTuFTjJiefW5t-IQ)\n   * [Coding TensorFlow](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvwLbzbnKJ59NkZvQAW9wLbx)\n   * [AskTensorFlow](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvypL1nu_65Uhf5LuWlZdmSL)\n   * [TensorFlow Meets](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvyOeER8UNF-1zXaCKGLZVog)\n   * [机器学习基础](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLOU2XLYxmsII9mzQ-Xxug4l2o04JBrkLV)\n   * [Powered by TensorFlow](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvyLQDomfBj-ptdBGTxAHwV_)\n   * [自然语言处理](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=fNxaJsNG3-s&list=PLQY2H8rRoyvzDbLUZkbudP-MFQZwNmU4S)\n   * [Inside TensorFlow](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQY2H8rRoyvzIuB8rZXs7pfyjiSUs8Vza)\n   \n### 课程  \u003Ca name=\"course\" \u002F>\n   * [TensorFlow 2.0完整教程 - 面向初学者的Python神经网络](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=6g4O5UOH304)\n   * [学习TensorFlow 2.0（Udemy）](https:\u002F\u002Fwww.udemy.com\u002Flearning-tensorflow-20\u002F)\n   * [TensorFlow实战专项课程](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Ftensorflow-in-practice)\n\n### 其他   \u003Ca name=\"Other_Video\" \u002F>\n   * [GTC Silicon Valley-2019 ID:S9495:TensorFlow 2.0简介](https:\u002F\u002Fdeveloper.nvidia.com\u002Fgtc\u002F2019\u002Fvideo\u002FS9495)\n   * [用Tensorflow 2.0赚钱](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=WS9Nckd2kq0)\n\n [\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_b69833744b2a.png\" alt=\"down\" width=\"30\" height=\"30\">  **回到顶部**](#TOC)\n\n## 博文 \u003Ca name=\"blogs\" \u002F>📃\n* [TensorFlow 2 模型迁移与新设计](https:\u002F\u002Fpgaleone.eu\u002Ftensorflow\u002Fgan\u002F2018\u002F11\u002F04\u002Ftensorflow-2-models-migration-and-new-design\u002F)\n* [以 Keras 为标准：TensorFlow 2.0 中高级 API 的指南](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fstandardizing-on-keras-guidance-on-high-level-apis-in-tensorflow-2-0-bad2b04c819a)\n* [抢先体验 TensorFlow 2.0 Alpha 版本](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Ftest-drive-tensorflow-2-0-alpha-b6dd1e522b01)\n* [2019 年 TensorFlow 开发者峰会回顾](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Frecap-of-the-2019-tensorflow-dev-summit-1b5ede42da8d)\n* [将代码升级到 TensorFlow 2.0](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fupgrading-your-code-to-tensorflow-2-0-f72c3a4d83b5)\n* [高效使用 TensorFlow 2.0：最佳实践与变化](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Feffective-tensorflow-2-0-best-practices-and-whats-changed-a0ca48767aff)\n* [TensorFlow 2.0 中的符号式与命令式 API 是什么？](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fwhat-are-symbolic-and-imperative-apis-in-tensorflow-2-0-dfccecb01021)\n* [TensorFlow 2.0 即将推出的内容](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fwhats-coming-in-tensorflow-2-0-d3663832e9b8)\n* [我对 TensorFlow 2.0 的笔记](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Ftesting-for-tensorflow-2-0-2db0d17c37f0)\n* [使用 TensorFlow 2.0 构建 Transformer 模型](https:\u002F\u002Fmachinetalk.org\u002F2019\u002F04\u002F29\u002Fcreate-the-transformer-with-tensorflow-2-0\u002F)\n* [Fast-SCNN 解析及基于 TensorFlow 2.0 的实现](https:\u002F\u002Fmedium.com\u002Fdeep-learning-journals\u002Ffast-scnn-explained-and-implemented-using-tensorflow-2-0-6bd17c17a49e)\n* [使用 TensorFlow 2.0 高级 API 进行图像分类](https:\u002F\u002Fhackernoon.com\u002Fimage-classification-with-tensorflow-2-0-d5a98bcffce1)\n* [基于 TensorFlow 2.0 的 Transformer 聊天机器人教程](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fa-transformer-chatbot-tutorial-with-tensorflow-2-0-88bf59e66fe2)\n* [使用 TensorFlow 2.0 轻松进行图像分类](https:\u002F\u002Ftowardsdatascience.com\u002Feasy-image-classification-with-tensorflow-2-0-f734fee52d13)\n* [在 TensorFlow 2.0 中实现自编码器](https:\u002F\u002Fmedium.com\u002F@abien.agarap\u002Fimplementing-an-autoencoder-in-tensorflow-2-0-5e86126e9f7)\n* [如何使用 Keras 在 TensorFlow 中构建宽深模型](https:\u002F\u002Ftowardsdatascience.com\u002Fhow-to-build-a-wide-and-deep-model-using-keras-in-tensorflow-2-0-2f7a236b5a4b)\n* [TensorFlow 2 中的心脏病预测](https:\u002F\u002Fmedium.com\u002F@curiousily\u002Fheart-disease-prediction-in-tensorflow-2-tensorflow-for-hackers-part-ii-378eef0400ee)\n* [使用 TensorFlow 2.0 生成文本](https:\u002F\u002Ftowardsdatascience.com\u002Fgenerating-text-with-tensorflow-2-0-6a65c7bdc568)\n* [TensorFlow 2.0 的十大重要更新](https:\u002F\u002Fwww.datacamp.com\u002Fcommunity\u002Ftutorials\u002Ften-important-updates-tensorflow)\n* [TensorFlow 2.0 全球文档冲刺速查表](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fhttps-medium-com-margaretmz-tf-docs-sprint-cheatsheet-7cb1dfd3e8b5)\n* [宣布 #PoweredByTF 2.0 开发者帖子挑战赛获奖者](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fannouncing-the-winners-of-the-poweredbytf-2-0-dev-post-challenge-af39d9d5a208)\n* [剖析 tf.function，揭示 AutoGraph 的优势与微妙之处](https:\u002F\u002Fpgaleone.eu\u002Ftensorflow\u002Ftf.function\u002F2019\u002F03\u002F21\u002Fdissecting-tf-function-part-1\u002F)\n* [使用 TensorFlow 2.0 进行信息论研究](https:\u002F\u002Fdev.to\u002Fmmithrakumar\u002Finformation-theory-with-tensorflow-2-0-29ao)\n* [便携式计算机视觉：树莓派上的 TensorFlow 2.0](https:\u002F\u002Ftowardsdatascience.com\u002Fportable-computer-vision-tensorflow-2-0-on-a-raspberry-pi-part-1-of-2-84e318798ce9)\n* [从 TensorFlow 1.0 到 PyTorch，再回到 TensorFlow 2.0](https:\u002F\u002Ftowardsdatascience.com\u002Ffrom-tensorflow-1-0-to-pytorch-back-to-tensorflow-2-0-f2f8a4c716b7)\n* [Hugging Face：用十行 TensorFlow 2.0 代码实现最先进自然语言处理](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fusing-tensorflow-2-for-state-of-the-art-natural-language-processing-102445cda54a)\n\n\n-----------------------------------------------------------------------------------------------------------------------\n* [TensorFlow 2.0 Alpha：在旧中寻找新意](https:\u002F\u002Fcv-tricks.com\u002Ftensorflow-tutorial\u002Ftensorflow-2-0-alpha\u002F)\n* [宣布 TensorFlow 2.0 Beta 版本](https:\u002F\u002Fwww.datacamp.com\u002Fcommunity\u002Ftutorials\u002Ften-important-updates-tensorflow)\n* [TensorFlow 2.0 现已发布！](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Ftensorflow-2-0-is-now-available-57d706c2a9ab)\n\n\n[\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_b69833744b2a.png\" alt=\"down\" width=\"30\" height=\"30\">  **返回顶部**](#TOC)\n\n## 其他 \u003Ca name=\"other\" \u002F>🌱\n### Python wheels  \u003Ca name=\"whls\" \u002F>🐍\n* [TensorFlow 2.1.0 Linux GPU（Compute 7.0、7.2、7.5）、Python 3.8、CUDA 10.2、cuDNN 7.6、AVX2、MKL、TensorRT 6](https:\u002F\u002Fgithub.com\u002Fyaroslavvb\u002Ftensorflow-community-wheels\u002Fissues\u002F140)\n* [TensorFlow 2.0.0、Python 3.7、Docker 镜像、无 AVX \u002F Nehalem-CPU 指令集 | Linux x86_64](https:\u002F\u002Fgithub.com\u002Fyaroslavvb\u002Ftensorflow-community-wheels\u002Fissues\u002F125)\n* [TensorFlow v2.0.0、Python 3.7、CUDA 10.0、cuDNN 7.6.4、无 AVX、Windows 10 x64](https:\u002F\u002Fgithub.com\u002Fyaroslavvb\u002Ftensorflow-community-wheels\u002Fissues\u002F127)\n* [TensorFlow 2.0、GPU（Compute Compatible 6.1、7.5）、CUDA 10.1、cuDNN 7.6、AVX、Python 3.6、MKL、XLA、CPU i3-8100、Ubuntu 18.04](https:\u002F\u002Fgithub.com\u002Fyaroslavvb\u002Ftensorflow-community-wheels\u002Fissues\u002F129)\n\n### 工具 \u003Ca name=\"tools\" \u002F>🔧\n* [TensorFlow 2.0 升级服务](https:\u002F\u002Fgithub.com\u002Flc0\u002Ftf2up)\n* [TensorFlow Hub](https:\u002F\u002Ftfhub.dev\u002Fs?q=tf2)\n* [Guild AI](https:\u002F\u002Fguild.ai)\n\n### #PoweredByTF 2.0 挑战\u003Ca name=\"PWBYTF2\" \u002F> 🔫 💣 🏆\n\n* [主页](https:\u002F\u002Ftensorflow.devpost.com\u002F)\n* [提交作品](https:\u002F\u002Ftensorflow.devpost.com\u002Fsubmissions)\n\n### 书籍 \u003Ca name=\"books\" \u002F>📚\n\n* [TensorFlow 2.0 快速入门指南](https:\u002F\u002Fwww.packtpub.com\u002Fbig-data-and-business-intelligence\u002Ftensorflow-20-quick-start-guide)\n* [动手学机器学习：使用 Scikit-Learn、Keras 和 TensorFlow，第二版](https:\u002F\u002Fwww.oreilly.com\u002Flibrary\u002Fview\u002Fhands-on-machine-learning\u002F9781492032632\u002F)\n* [TensorFlow 机器学习 Cookbook - 第二版](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fannouncing-tensorflow-2-0-beta-abb24bbfbe3d)\n* [TensorFlow 2 in Action](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Ftensorflow-in-action)\n\n[\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_readme_b69833744b2a.png\" alt=\"down\" width=\"30\" height=\"30\">  **返回顶部**](#TOC)\n\n## 贡献 📭  \u003Ca name=\"contributions\" \u002F>\n\n我们始终欢迎您的贡献！\n\n如果您想为本列表做出贡献（请务必这样做），请向我发送拉取请求。此外，如果您发现上述任何仓库因以下原因应被弃用：\n\n* 仓库所有者明确表示“此库不再维护”。\n* 长期未进行提交（2~3年）。\n\n更多详情请参阅[贡献指南](https:\u002F\u002Fgithub.com\u002FAmin-Tgz\u002FAwesome-TensorFlow-2\u002Fblob\u002Fmaster\u002Fcontributing.md)\n\n## 许可证\n根据 [知识共享 CC0 许可协议](https:\u002F\u002Fcreativecommons.org\u002Fpublicdomain\u002Fzero\u002F1.0\u002F) 授权。","# Awesome TensorFlow 2 快速上手指南\n\n`awesome-tensorflow-2` 是一个精选的 TensorFlow v2 教程、博客和项目资源列表。本指南旨在帮助开发者快速搭建环境并掌握 TF2 的核心特性（如即时执行 Eager Execution 和高级 API）。\n\n## 1. 环境准备\n\n在开始之前，请确保您的系统满足以下要求：\n\n*   **操作系统**：Windows, macOS, 或 Linux (Ubuntu 推荐)\n*   **Python 版本**：Python 3.6 - 3.8 (根据 TF 2.3 发布时的兼容性，建议 Python 3.7+)\n*   **硬件加速（可选但推荐）**：\n    *   NVIDIA GPU\n    *   CUDA Toolkit: `10.1`\n    *   cuDNN SDK: `7.6`\n    *   *注意：若仅使用 CPU 进行学习和小规模实验，无需安装 CUDA\u002FcuDNN。*\n\n## 2. 安装步骤\n\n推荐使用 `pip` 进行安装。为了获得更好的下载速度，中国开发者建议使用国内镜像源（如清华大学或阿里云镜像）。\n\n### 基础安装（CPU 版本）\n\n```bash\npip install tensorflow -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n### GPU 版本安装\n\n如果您已正确配置了 CUDA 10.1 和 cuDNN 7.6，可以直接安装包含 GPU 支持的版本（TF2 早期版本中 GPU 支持通常包含在主包中，或需安装 `tensorflow-gpu`，具体取决于子版本，TF 2.3+ 通常统一为 `tensorflow`）：\n\n```bash\npip install tensorflow -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n### 验证安装\n\n在终端或命令行中运行以下命令，检查是否安装成功及版本信息：\n\n```python\npython -c \"import tensorflow as tf; print(tf.reduce_sum(tf.random.normal([1000, 1000])))\"\n```\n\n如果输出了一个张量值且无报错，说明安装成功。\n\n## 3. 基本使用\n\nTensorFlow 2 默认启用 **Eager Execution**（即时执行），使得代码更像标准的 Python 代码，易于调试和理解。以下是使用 `tf.keras` 构建一个简单的神经网络的示例。\n\n### 简单示例：手写数字识别 (MNIST)\n\n```python\nimport tensorflow as tf\n\n# 1. 加载数据集\nmnist = tf.keras.datasets.mnist\n(x_train, y_train), (x_test, y_test) = mnist.load_data()\n\n# 2. 数据预处理：归一化到 [0, 1]\nx_train, x_test = x_train \u002F 255.0, x_test \u002F 255.0\n\n# 3. 构建模型\nmodel = tf.keras.models.Sequential([\n  tf.keras.layers.Flatten(input_shape=(28, 28)),\n  tf.keras.layers.Dense(128, activation='relu'),\n  tf.keras.layers.Dropout(0.2),\n  tf.keras.layers.Dense(10, activation='softmax')\n])\n\n# 4. 编译模型\nmodel.compile(optimizer='adam',\n              loss='sparse_categorical_crossentropy',\n              metrics=['accuracy'])\n\n# 5. 训练模型\nmodel.fit(x_train, y_train, epochs=5)\n\n# 6. 评估模型\nmodel.evaluate(x_test,  y_test, verbose=2)\n```\n\n### 核心优势体验\n\n*   **简洁性**：如上所示，使用 `tf.keras` 高层 API 可以快速搭建模型。\n*   **即时执行**：你可以直接在 Python 中打印张量的值，无需启动 Session。\n    ```python\n    a = tf.constant([[1.0, 2.0], [3.0, 4.0]])\n    b = tf.constant([[1.0, 1.0], [0.0, 1.0]])\n    print(a + b)  # 直接输出结果\n    ```\n\n## 4. 进阶学习资源推荐\n\n根据 `awesome-tensorflow-2` 收录的内容，建议按以下路径深入学习：\n\n1.  **官方文档与教程**：\n    *   [TensorFlow 官方快速入门](https:\u002F\u002Fwww.tensorflow.org\u002Ftutorials\u002Fquickstart\u002Fbeginner)\n    *   [Effective TensorFlow 2](https:\u002F\u002Fwww.tensorflow.org\u002Fguide\u002Feffective_tf2)：了解 TF2 的最佳实践和迁移指南。\n\n2.  **优质开源教程**：\n    *   [TensorFlow-2.x-Tutorials](https:\u002F\u002Fgithub.com\u002Fdragen1860\u002FTensorFlow-2.x-Tutorials)：涵盖从基础到高级的全面教程。\n    *   [Tensorflow2_tutorials_chinese](https:\u002F\u002Fgithub.com\u002Fczy36mengfei\u002Ftensorflow2_tutorials_chinese)：适合中文读者的教程集合。\n\n3.  **特定领域项目**：\n    *   **NLP**: [Hugging Face Transformers](https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Ftransformers) (支持 TF2)\n    *   **目标检测**: [YOLO v3 for TF2](https:\u002F\u002Fgithub.com\u002Fzzh8829\u002Fyolov3-tf2)\n    *   **生成模型 (GAN)**: [CycleGAN-Tensorflow-2](https:\u002F\u002Fgithub.com\u002FLynnHo\u002FCycleGAN-Tensorflow-2)\n\n通过结合官方文档与上述开源项目，您可以快速掌握 TensorFlow 2 在实际开发中的应用。","某初创公司的算法工程师李明，正负责将团队原有的 TensorFlow 1.x 图像分类模型迁移至 TF 2.x，并计划新增一个基于生成对抗网络（GAN）的数据增强模块，以解决训练数据不足的问题。\n\n### 没有 awesome-tensorflow-2 时\n- **学习路径混乱**：面对 TF 2.x 推崇的 Eager Execution 和 Keras 高层 API，李明在海量且过时的博客中迷失，难以区分哪些是 1.x 的旧写法，哪些是 2.x 的最佳实践，导致大量时间浪费在试错上。\n- **特定领域代码难寻**：在开发 GAN 模块时，官方文档仅提供了基础示例，缺乏针对复杂场景的完整项目参考。李明不得不从零搭建架构，调试梯度消失等问题耗费了数天精力。\n- **资源筛选成本高**：为了寻找高质量的视频教程和中文资料，他需要在 GitHub、YouTube 和各大技术论坛间反复跳转，信息碎片化严重，难以形成系统性的知识体系。\n- **环境配置踩坑**：由于不清楚 TF 2.3 与 CUDA\u002FcuDNN 的具体版本依赖关系，他在本地环境配置上多次失败，阻碍了开发进度。\n\n### 使用 awesome-tensorflow-2 后\n- **精准获取最佳实践**：通过 curated 的教程列表，李明直接锁定了针对 TF 2.x 的“Effective TF2”指南和优质中文教程，快速掌握了从 Session 模式到 Eager 模式的思维转换，避免了语法混淆。\n- **复用成熟项目代码**：在“Specific Model\u002FTask”板块中，他找到了多个高质量的 GAN 开源项目作为基准（Baseline），直接复用其网络结构和训练技巧，将模块开发时间从一周缩短至两天。\n- **系统化学习资源**：借助整理好的视频清单（如 TensorFlow World 2019），他利用通勤时间系统学习了新特性，并通过链接到的书籍和博客深化理解，构建了完整的知识框架。\n- **明确的环境指引**：README 中清晰标注了安装所需的 CUDA 10.1 和 cuDNN 7.6 版本要求，让他一次性成功配置好 GPU 环境，消除了底层兼容性问题。\n\nawesome-tensorflow-2 通过高度结构化的资源聚合，将开发者从信息噪音中解放出来，显著降低了 TensorFlow 2.x 的学习曲线与工程落地门槛。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FAmin-Tgz_awesome-tensorflow-2_d16a3b40.png","Amin-Tgz","Amin Taghizadeh","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FAmin-Tgz_224956a1.jpg","Instead of being a specialist, I love to be a multipotentialite!","IUT_University","Isfahan , Iran","taghizadeh.amin72@gmail.com",null,"https:\u002F\u002Fgithub.com\u002FAmin-Tgz",523,102,"2026-03-30T05:02:47","CC0-1.0",1,"未说明","若使用 GPU 版本，需要 NVIDIA GPU，CUDA 10.1，cuDNN 7.6",{"notes":93,"python":90,"dependencies":94},"这是一个 TensorFlow 2 的资源列表（教程、博客、项目集合），而非单一可执行软件。文中提到的具体安装需求（CUDA 10.1 & cuDNN 7.6）是针对 TensorFlow 2.2\u002F2.3 版本的官方建议。实际运行列表中各个子项目时，需参考各子项目的具体依赖要求。",[95,96],"tensorflow>=2.3","keras",[14,13,26],[99,100,101,102,103,104,105,106,107,108,109,110,111,112,113],"tensorflow2","awesome","tensorflow-2","tensorflow-2-example","tensorflow2-awesome","tf2","yolo","nlp","tf2gan","tf2cnn","tensorflow2-models","tensorflow2-experiments","tf2-example","tf2-segmentation","tensorflow","2026-03-27T02:49:30.150509","2026-04-06T07:14:06.525174",[],[]]