[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-tensorflow--tfjs":3,"tool-tensorflow--tfjs":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",150037,2,"2026-04-10T23:33:47",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",108322,"2026-04-10T11:39:34",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":72,"owner_avatar_url":73,"owner_bio":74,"owner_company":75,"owner_location":75,"owner_email":76,"owner_twitter":75,"owner_website":77,"owner_url":78,"languages":79,"stars":119,"forks":120,"last_commit_at":121,"license":122,"difficulty_score":32,"env_os":123,"env_gpu":123,"env_ram":123,"env_deps":124,"category_tags":131,"github_topics":132,"view_count":143,"oss_zip_url":75,"oss_zip_packed_at":75,"status":17,"created_at":144,"updated_at":145,"faqs":146,"releases":173},584,"tensorflow\u002Ftfjs","tfjs","A WebGL accelerated JavaScript library for training and deploying ML models.","tfjs 是一个基于 JavaScript 的开源机器学习库，旨在让开发者能够在浏览器和 Node.js 环境中无缝地训练和部署模型。它解决了传统 AI 应用必须依赖后端服务器的痛点，实现了模型推理和训练的前端化，不仅大幅降低了延迟，还确保了用户数据无需离开本地设备，有效保护了隐私。tfjs 非常适合前端工程师、全栈开发者以及希望在 Web 端进行 AI 原型研究的研究人员。通过 WebGL、WebAssembly 或 WebGPU 等技术，它能充分利用客户端硬件性能进行加速。对于已有 TensorFlow 模型的团队，tfjs 提供了便捷的转换工具，支持直接复用现有资产。此外，它还内置了可视化组件和 AutoML 接口，降低了使用门槛。无论是从零构建神经网络，还是加载预训练模型，tfjs 都能提供灵活且直观的 API 支持，助力打造高性能的 Web AI 应用。","# TensorFlow.js\n\nTensorFlow.js is an open-source hardware-accelerated JavaScript library for\ntraining and deploying machine learning models.\n\n\n**Develop ML in the Browser** \u003Cbr\u002F>\nUse flexible and intuitive APIs to build models from scratch using the low-level\nJavaScript linear algebra library or the high-level layers API.\n\n**Develop ML in Node.js** \u003Cbr\u002F>\nExecute native TensorFlow with the same TensorFlow.js API under the Node.js\nruntime.\n\n**Run Existing models** \u003Cbr\u002F>\nUse TensorFlow.js model converters to run pre-existing TensorFlow models right\nin the browser.\n\n**Retrain Existing models** \u003Cbr\u002F>\nRetrain pre-existing ML models using sensor data connected to the browser or\nother client-side data.\n\n## About this repo\n\nThis repository contains the logic and scripts that combine\nseveral packages.\n\nAPIs:\n- [TensorFlow.js Core](\u002Ftfjs-core),\n  a flexible low-level API for neural networks and numerical computation.\n- [TensorFlow.js Layers](\u002Ftfjs-layers),\n  a high-level API which implements functionality similar to\n  [Keras](https:\u002F\u002Fkeras.io\u002F).\n- [TensorFlow.js Data](\u002Ftfjs-data),\n  a simple API to load and prepare data analogous to\n  [tf.data](https:\u002F\u002Fwww.tensorflow.org\u002Fguide\u002Fdatasets).\n- [TensorFlow.js Converter](\u002Ftfjs-converter),\n  tools to import a TensorFlow SavedModel to TensorFlow.js\n- [TensorFlow.js Vis](\u002Ftfjs-vis),\n  in-browser visualization for TensorFlow.js models\n- [TensorFlow.js AutoML](\u002Ftfjs-automl),\n  Set of APIs to load and run models produced by\n  [AutoML Edge](https:\u002F\u002Fcloud.google.com\u002Fvision\u002Fautoml\u002Fdocs\u002Fedge-quickstart).\n\n\nBackends\u002FPlatforms:\n- [TensorFlow.js CPU Backend](\u002Ftfjs-backend-cpu), pure-JS backend for Node.js and the browser.\n- [TensorFlow.js WebGL Backend](\u002Ftfjs-backend-webgl), WebGL backend for the browser.\n- [TensorFlow.js WASM Backend](\u002Ftfjs-backend-wasm), WebAssembly backend for the browser.\n- [TensorFlow.js WebGPU](\u002Ftfjs-backend-webgpu), WebGPU backend for the browser.\n- [TensorFlow.js Node](\u002Ftfjs-node), Node.js platform via TensorFlow C++ adapter.\n- [TensorFlow.js React Native](\u002Ftfjs-react-native), React Native platform via expo-gl adapter.\n\nIf you care about bundle size, you can import those packages individually.\n\nIf you are looking for Node.js support, check out the [TensorFlow.js Node directory](\u002Ftfjs-node).\n\n## Examples\n\nCheck out our\n[examples repository](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs-examples)\nand our [tutorials](https:\u002F\u002Fjs.tensorflow.org\u002Ftutorials\u002F).\n\n## Gallery\n\nBe sure to check out [the gallery](GALLERY.md) of all projects related to TensorFlow.js.\n\n## Pre-trained models\n\nBe sure to also check out our [models repository](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs-models) where we host pre-trained models\non NPM.\n\n## Benchmarks\n\n* [Local benchmark tool](https:\u002F\u002Ftfjs-benchmarks.web.app\u002F). Use this webpage tool to collect the performance related metrics (speed, memory, etc) of TensorFlow.js models and kernels **on your local device** with CPU, WebGL or WASM backends. You can benchmark custom models by following this [guide](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fblob\u002Fmaster\u002Fe2e\u002Fbenchmarks\u002Flocal-benchmark\u002FREADME.md).\n* [Multi-device benchmark tool](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Ftree\u002Fmaster\u002Fe2e\u002Fbenchmarks\u002Fbrowserstack-benchmark\u002FREADME.md). Use this tool to collect the same performance related metrics **on a collection of remote devices**.\n\n## Getting started\n\nThere are two main ways to get TensorFlow.js in your JavaScript project:\nvia \u003Ca href=\"https:\u002F\u002Fdeveloper.mozilla.org\u002Fen-US\u002Fdocs\u002FLearn\u002FHTML\u002FHowto\u002FUse_JavaScript_within_a_webpage\" target=\"_blank\">script tags\u003C\u002Fa> \u003Cstrong>or\u003C\u002Fstrong> by installing it from \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002F\" target=\"_blank\">NPM\u003C\u002Fa>\nand using a build tool like \u003Ca href=\"https:\u002F\u002Fparceljs.org\u002F\" target=\"_blank\">Parcel\u003C\u002Fa>,\n\u003Ca href=\"https:\u002F\u002Fwebpack.js.org\u002F\" target=\"_blank\">WebPack\u003C\u002Fa>, or \u003Ca href=\"https:\u002F\u002Frollupjs.org\u002Fguide\u002Fen\" target=\"_blank\">Rollup\u003C\u002Fa>.\n\n### via Script Tag\n\nAdd the following code to an HTML file:\n\n```html\n\u003Chtml>\n  \u003Chead>\n    \u003C!-- Load TensorFlow.js -->\n    \u003Cscript src=\"https:\u002F\u002Fcdn.jsdelivr.net\u002Fnpm\u002F@tensorflow\u002Ftfjs\u002Fdist\u002Ftf.min.js\"> \u003C\u002Fscript>\n\n\n    \u003C!-- Place your code in the script tag below. You can also use an external .js file -->\n    \u003Cscript>\n      \u002F\u002F Notice there is no 'import' statement. 'tf' is available on the index-page\n      \u002F\u002F because of the script tag above.\n\n      \u002F\u002F Define a model for linear regression.\n      const model = tf.sequential();\n      model.add(tf.layers.dense({units: 1, inputShape: [1]}));\n\n      \u002F\u002F Prepare the model for training: Specify the loss and the optimizer.\n      model.compile({loss: 'meanSquaredError', optimizer: 'sgd'});\n\n      \u002F\u002F Generate some synthetic data for training.\n      const xs = tf.tensor2d([1, 2, 3, 4], [4, 1]);\n      const ys = tf.tensor2d([1, 3, 5, 7], [4, 1]);\n\n      \u002F\u002F Train the model using the data.\n      model.fit(xs, ys).then(() => {\n        \u002F\u002F Use the model to do inference on a data point the model hasn't seen before:\n        \u002F\u002F Open the browser devtools to see the output\n        model.predict(tf.tensor2d([5], [1, 1])).print();\n      });\n    \u003C\u002Fscript>\n  \u003C\u002Fhead>\n\n  \u003Cbody>\n  \u003C\u002Fbody>\n\u003C\u002Fhtml>\n```\n\nOpen up that HTML file in your browser, and the code should run!\n\n### via NPM\n\nAdd TensorFlow.js to your project using \u003Ca href=\"https:\u002F\u002Fyarnpkg.com\u002Fen\u002F\" target=\"_blank\">yarn\u003C\u002Fa> \u003Cem>or\u003C\u002Fem> \u003Ca href=\"https:\u002F\u002Fdocs.npmjs.com\u002Fcli\u002Fnpm\" target=\"_blank\">npm\u003C\u002Fa>. \u003Cb>Note:\u003C\u002Fb> Because\nwe use ES2017 syntax (such as `import`), this workflow assumes you are using a modern browser or a bundler\u002Ftranspiler\nto convert your code to something older browsers understand. See our\n\u003Ca href='https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs-examples' target=\"_blank\">examples\u003C\u002Fa>\nto see how we use \u003Ca href=\"https:\u002F\u002Fparceljs.org\u002F\" target=\"_blank\">Parcel\u003C\u002Fa> to build\nour code. However, you are free to use any build tool that you prefer.\n\n\n\n```js\nimport * as tf from '@tensorflow\u002Ftfjs';\n\n\u002F\u002F Define a model for linear regression.\nconst model = tf.sequential();\nmodel.add(tf.layers.dense({units: 1, inputShape: [1]}));\n\n\u002F\u002F Prepare the model for training: Specify the loss and the optimizer.\nmodel.compile({loss: 'meanSquaredError', optimizer: 'sgd'});\n\n\u002F\u002F Generate some synthetic data for training.\nconst xs = tf.tensor2d([1, 2, 3, 4], [4, 1]);\nconst ys = tf.tensor2d([1, 3, 5, 7], [4, 1]);\n\n\u002F\u002F Train the model using the data.\nmodel.fit(xs, ys).then(() => {\n  \u002F\u002F Use the model to do inference on a data point the model hasn't seen before:\n  model.predict(tf.tensor2d([5], [1, 1])).print();\n});\n```\n\nSee our \u003Ca href=\"https:\u002F\u002Fjs.tensorflow.org\u002Ftutorials\u002F\" target=\"_blank\">tutorials\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs-examples\" target=\"_blank\">examples\u003C\u002Fa>\nand \u003Ca href=\"https:\u002F\u002Fjs.tensorflow.org\u002Fapi\u002Flatest\u002F\">documentation\u003C\u002Fa> for more details.\n\n## Importing pre-trained models\n\nWe support porting pre-trained models from:\n- [TensorFlow SavedModel](https:\u002F\u002Fwww.tensorflow.org\u002Fjs\u002Ftutorials\u002Fconversion\u002Fimport_saved_model)\n- [Keras](https:\u002F\u002Fjs.tensorflow.org\u002Ftutorials\u002Fimport-keras.html)\n\n## Various ops supported in different backends\n\nPlease refer below :\n- [TFJS Ops Matrix](https:\u002F\u002Fdocs.google.com\u002Fspreadsheets\u002Fd\u002F1D25XtWaBrmUEErbGQB0QmNhH-xtwHo9LDl59w0TbxrI\u002Fedit#gid=0)\n\n## Find out more\n\n[TensorFlow.js](https:\u002F\u002Fjs.tensorflow.org) is a part of the\n[TensorFlow](https:\u002F\u002Fwww.tensorflow.org) ecosystem. For more info:\n- For help from the community, use the `tfjs` tag on the [TensorFlow Forum](https:\u002F\u002Fdiscuss.tensorflow.org\u002Ftag\u002Ftfjs).\n- [TensorFlow.js Website](https:\u002F\u002Fjs.tensorflow.org)\n- [Tutorials](https:\u002F\u002Fjs.tensorflow.org\u002Ftutorials)\n- [API reference](https:\u002F\u002Fjs.tensorflow.org\u002Fapi\u002Flatest\u002F)\n- [TensorFlow.js Blog](https:\u002F\u002Fblog.tensorflow.org\u002Fsearch?label=TensorFlow.js)\n\nThanks, \u003Ca href=\"https:\u002F\u002Fwww.browserstack.com\u002F\">BrowserStack\u003C\u002Fa>, for providing testing support.\n","# TensorFlow.js\n\nTensorFlow.js 是一个开源的、硬件加速的 JavaScript 库，用于训练和部署机器学习模型。\n\n**在浏览器中开发机器学习** \u003Cbr\u002F>\n使用灵活直观的 API (应用程序编程接口) 通过底层的 JavaScript 线性代数库或高层的层 API 从头构建模型。\n\n**在 Node.js 中开发机器学习** \u003Cbr\u002F>\n在 Node.js 运行时环境下，使用相同的 TensorFlow.js API 执行原生 TensorFlow。\n\n**运行现有模型** \u003Cbr\u002F>\n使用 TensorFlow.js 模型转换器直接在浏览器中运行现有的 TensorFlow 模型。\n\n**重新训练现有模型** \u003Cbr\u002F>\n使用连接到浏览器的传感器数据或其他客户端数据重新训练现有的机器学习模型。\n\n## 关于此仓库\n\n此仓库包含组合多个包的逻辑和脚本。\n\nAPIs (应用程序编程接口):\n- [TensorFlow.js Core](\u002Ftfjs-core)，用于神经网络和数值计算的灵活底层 API。\n- [TensorFlow.js Layers](\u002Ftfjs-layers)，实现类似 [Keras](https:\u002F\u002Fkeras.io\u002F) 功能的高层 API。\n- [TensorFlow.js Data](\u002Ftfjs-data)，加载和准备数据的简单 API，类似于 [tf.data](https:\u002F\u002Fwww.tensorflow.org\u002Fguide\u002Fdatasets)。\n- [TensorFlow.js Converter](\u002Ftfjs-converter)，将 TensorFlow SavedModel 导入 TensorFlow.js 的工具。\n- [TensorFlow.js Vis](\u002Ftfjs-vis)，TensorFlow.js 模型的浏览器内可视化。\n- [TensorFlow.js AutoML](\u002Ftfjs-automl)，一组用于加载和运行由 [AutoML Edge](https:\u002F\u002Fcloud.google.com\u002Fvision\u002Fautoml\u002Fdocs\u002Fedge-quickstart) 生成的模型的 API。\n\n后端\u002F平台:\n- [TensorFlow.js CPU Backend](\u002Ftfjs-backend-cpu)，Node.js 和浏览器的纯 JavaScript 后端。\n- [TensorFlow.js WebGL Backend](\u002Ftfjs-backend-webgl)，浏览器的 WebGL 后端。\n- [TensorFlow.js WASM Backend](\u002Ftfjs-backend-wasm)，浏览器的 WebAssembly 后端。\n- [TensorFlow.js WebGPU](\u002Ftfjs-backend-webgpu)，浏览器的 WebGPU 后端。\n- [TensorFlow.js Node](\u002Ftfjs-node)，通过 TensorFlow C++ 适配器的 Node.js 平台。\n- [TensorFlow.js React Native](\u002Ftfjs-react-native)，通过 expo-gl 适配器的 React Native 平台。\n\n如果您关心打包大小，可以单独导入这些包。\n\n如果您正在寻找 Node.js 支持，请查看 [TensorFlow.js Node 目录](\u002Ftfjs-node)。\n\n## 示例\n\n查看我们的 [示例仓库](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs-examples) 和 [教程](https:\u002F\u002Fjs.tensorflow.org\u002Ftutorials\u002F)。\n\n## 画廊\n\n请务必查看 [画廊](GALLERY.md) 中所有与 TensorFlow.js 相关的项目。\n\n## 预训练模型\n\n也请务必查看我们的 [模型仓库](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs-models)，我们在其中托管了预训练模型到 NPM。\n\n## 基准测试\n\n* [本地基准测试工具](https:\u002F\u002Ftfjs-benchmarks.web.app\u002F)。使用此网页工具收集 TensorFlow.js 模型和内核在您的本地设备上使用 CPU、WebGL 或 WASM 后端时的性能相关指标（速度、内存等）。您可以按照此 [指南](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fblob\u002Fmaster\u002Fe2e\u002Fbenchmarks\u002Flocal-benchmark\u002FREADME.md) 对自定义模型进行基准测试。\n* [多设备基准测试工具](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Ftree\u002Fmaster\u002Fe2e\u002Fbenchmarks\u002Fbrowserstack-benchmark\u002FREADME.md)。使用此工具收集相同性能相关指标，但针对的是一组远程设备。\n\n## 入门\n\n将 TensorFlow.js 集成到您的 JavaScript 项目中有两种主要方式：通过 \u003Ca href=\"https:\u002F\u002Fdeveloper.mozilla.org\u002Fen-US\u002Fdocs\u002FLearn\u002FHTML\u002FHowto\u002FUse_JavaScript_within_a_webpage\" target=\"_blank\">script 标签\u003C\u002Fa> \u003Cstrong>或者\u003C\u002Fstrong> 从 \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002F\" target=\"_blank\">NPM\u003C\u002Fa> 安装它并使用构建工具如 \u003Ca href=\"https:\u002F\u002Fparceljs.org\u002F\" target=\"_blank\">Parcel\u003C\u002Fa>、\u003Ca href=\"https:\u002F\u002Fwebpack.js.org\u002F\" target=\"_blank\">WebPack\u003C\u002Fa> 或 \u003Ca href=\"https:\u002F\u002Frollupjs.org\u002Fguide\u002Fen\" target=\"_blank\">Rollup\u003C\u002Fa>。\n\n### 通过 Script Tag\n\n将以下代码添加到 HTML 文件中：\n\n```html\n\u003Chtml>\n  \u003Chead>\n    \u003C!-- Load TensorFlow.js -->\n    \u003Cscript src=\"https:\u002F\u002Fcdn.jsdelivr.net\u002Fnpm\u002F@tensorflow\u002Ftfjs\u002Fdist\u002Ftf.min.js\"> \u003C\u002Fscript>\n\n\n    \u003C!-- Place your code in the script tag below. You can also use an external .js file -->\n    \u003Cscript>\n      \u002F\u002F Notice there is no 'import' statement. 'tf' is available on the index-page\n      \u002F\u002F because of the script tag above.\n\n      \u002F\u002F Define a model for linear regression.\n      const model = tf.sequential();\n      model.add(tf.layers.dense({units: 1, inputShape: [1]}));\n\n      \u002F\u002F Prepare the model for training: Specify the loss and the optimizer.\n      model.compile({loss: 'meanSquaredError', optimizer: 'sgd'});\n\n      \u002F\u002F Generate some synthetic data for training.\n      const xs = tf.tensor2d([1, 2, 3, 4], [4, 1]);\n      const ys = tf.tensor2d([1, 3, 5, 7], [4, 1]);\n\n      \u002F\u002F Train the model using the data.\n      model.fit(xs, ys).then(() => {\n        \u002F\u002F Use the model to do inference on a data point the model hasn't seen before:\n        \u002F\u002F Open the browser devtools to see the output\n        model.predict(tf.tensor2d([5], [1, 1])).print();\n      });\n    \u003C\u002Fscript>\n  \u003C\u002Fhead>\n\n  \u003Cbody>\n  \u003C\u002Fbody>\n\u003C\u002Fhtml>\n```\n\n在浏览器中打开该 HTML 文件，代码应该就能运行了！\n\n### 通过 NPM\n\n使用 \u003Ca href=\"https:\u002F\u002Fyarnpkg.com\u002Fen\u002F\" target=\"_blank\">yarn\u003C\u002Fa> \u003Cem>或\u003C\u002Fem> \u003Ca href=\"https:\u002F\u002Fdocs.npmjs.com\u002Fcli\u002Fnpm\" target=\"_blank\">npm\u003C\u002Fa> 将 TensorFlow.js 添加到您的项目中。\u003Cb>注意：\u003C\u002Fb> 因为我们使用 ES2017 语法（例如 `import`），此工作流程假设您使用的是现代浏览器或使用打包器\u002F转译器将代码转换为旧版浏览器能理解的内容。查看我们的 \u003Ca href='https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs-examples' target=\"_blank\">示例\u003C\u002Fa> 以了解我们如何使用 \u003Ca href=\"https:\u002F\u002Fparceljs.org\u002F\" target=\"_blank\">Parcel\u003C\u002Fa> 构建代码。但是，您可以自由使用任何您喜欢的构建工具。\n\n\n\n```js\nimport * as tf from '@tensorflow\u002Ftfjs';\n\n\u002F\u002F Define a model for linear regression.\nconst model = tf.sequential();\nmodel.add(tf.layers.dense({units: 1, inputShape: [1]}));\n\n\u002F\u002F Prepare the model for training: Specify the loss and the optimizer.\nmodel.compile({loss: 'meanSquaredError', optimizer: 'sgd'});\n\n\u002F\u002F Generate some synthetic data for training.\nconst xs = tf.tensor2d([1, 2, 3, 4], [4, 1]);\nconst ys = tf.tensor2d([1, 3, 5, 7], [4, 1]);\n\n\u002F\u002F Train the model using the data.\nmodel.fit(xs, ys).then(() => {\n  \u002F\u002F Use the model to do inference on a data point the model hasn't seen before:\n  model.predict(tf.tensor2d([5], [1, 1])).print();\n});\n```\n\n有关更多详细信息，请参阅我们的 \u003Ca href=\"https:\u002F\u002Fjs.tensorflow.org\u002Ftutorials\u002F\" target=\"_blank\">教程\u003C\u002Fa>、\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs-examples\" target=\"_blank\">示例\u003C\u002Fa> 和 \u003Ca href=\"https:\u002F\u002Fjs.tensorflow.org\u002Fapi\u002Flatest\u002F\">文档\u003C\u002Fa>。\n\n## 导入预训练模型\n\n我们支持从以下来源移植预训练模型：\n- [TensorFlow SavedModel](https:\u002F\u002Fwww.tensorflow.org\u002Fjs\u002Ftutorials\u002Fconversion\u002Fimport_saved_model)\n- [Keras](https:\u002F\u002Fjs.tensorflow.org\u002Ftutorials\u002Fimport-keras.html)\n\n## 不同后端支持的各类算子\n\n请参考以下内容：\n- [TFJS 算子矩阵](https:\u002F\u002Fdocs.google.com\u002Fspreadsheets\u002Fd\u002F1D25XtWaBrmUEErbGQB0QmNhH-xtwHo9LDl59w0TbxrI\u002Fedit#gid=0)\n\n## 了解更多\n\n[TensorFlow.js](https:\u002F\u002Fjs.tensorflow.org) 是 [TensorFlow](https:\u002F\u002Fwww.tensorflow.org) 生态系统的一部分。更多信息：\n- 如需社区帮助，请在 [TensorFlow 论坛](https:\u002F\u002Fdiscuss.tensorflow.org\u002Ftag\u002Ftfjs) 使用 `tfjs` 标签。\n- [TensorFlow.js 网站](https:\u002F\u002Fjs.tensorflow.org)\n- [教程](https:\u002F\u002Fjs.tensorflow.org\u002Ftutorials)\n- [API 参考](https:\u002F\u002Fjs.tensorflow.org\u002Fapi\u002Flatest\u002F)\n- [TensorFlow.js 博客](https:\u002F\u002Fblog.tensorflow.org\u002Fsearch?label=TensorFlow.js)\n\n感谢 \u003Ca href=\"https:\u002F\u002Fwww.browserstack.com\u002F\">BrowserStack\u003C\u002Fa> 提供测试支持。","# TensorFlow.js 快速上手指南\n\nTensorFlow.js 是一个开源的硬件加速 JavaScript 库，支持在浏览器和 Node.js 环境中训练和部署机器学习模型。\n\n## 环境准备\n\n- **浏览器**: 支持主流现代浏览器（Chrome, Firefox, Safari, Edge 等）。\n- **Node.js**: 推荐使用 v10+ 版本（适用于 NPM 安装方式）。\n- **构建工具**: 若使用 NPM 方式，建议配合 Webpack、Parcel 或 Rollup 等打包工具使用。\n\n## 安装步骤\n\n### 方式一：通过 NPM 安装（推荐用于项目）\n\n使用 yarn 或 npm 将 TensorFlow.js 添加到项目中。\n\n```bash\nnpm install @tensorflow\u002Ftfjs\n```\n\n> **提示**: 国内开发者可使用淘宝镜像加速下载：\n> ```bash\n> npm config set registry https:\u002F\u002Fregistry.npmmirror.com\n> npm install @tensorflow\u002Ftfjs\n> ```\n\n### 方式二：通过 Script Tag（适合快速原型）\n\n在 HTML 文件中直接引入 CDN 链接：\n\n```html\n\u003Cscript src=\"https:\u002F\u002Fcdn.jsdelivr.net\u002Fnpm\u002F@tensorflow\u002Ftfjs\u002Fdist\u002Ftf.min.js\"> \u003C\u002Fscript>\n```\n\n## 基本使用\n\n以下示例演示如何定义一个简单的线性回归模型并进行训练。\n\n### NPM 方式代码示例\n\n```js\nimport * as tf from '@tensorflow\u002Ftfjs';\n\n\u002F\u002F Define a model for linear regression.\nconst model = tf.sequential();\nmodel.add(tf.layers.dense({units: 1, inputShape: [1]}));\n\n\u002F\u002F Prepare the model for training: Specify the loss and the optimizer.\nmodel.compile({loss: 'meanSquaredError', optimizer: 'sgd'});\n\n\u002F\u002F Generate some synthetic data for training.\nconst xs = tf.tensor2d([1, 2, 3, 4], [4, 1]);\nconst ys = tf.tensor2d([1, 3, 5, 7], [4, 1]);\n\n\u002F\u002F Train the model using the data.\nmodel.fit(xs, ys).then(() => {\n  \u002F\u002F Use the model to do inference on a data point the model hasn't seen before:\n  model.predict(tf.tensor2d([5], [1, 1])).print();\n});\n```\n\n### Script Tag 方式代码示例\n\n无需 `import` 语句，直接使用全局变量 `tf`：\n\n```html\n\u003Cscript>\n  \u002F\u002F Notice there is no 'import' statement. 'tf' is available on the index-page\n  \u002F\u002F because of the script tag above.\n\n  \u002F\u002F Define a model for linear regression.\n  const model = tf.sequential();\n  model.add(tf.layers.dense({units: 1, inputShape: [1]}));\n\n  \u002F\u002F Prepare the model for training: Specify the loss and the optimizer.\n  model.compile({loss: 'meanSquaredError', optimizer: 'sgd'});\n\n  \u002F\u002F Generate some synthetic data for training.\n  const xs = tf.tensor2d([1, 2, 3, 4], [4, 1]);\n  const ys = tf.tensor2d([1, 3, 5, 7], [4, 1]);\n\n  \u002F\u002F Train the model using the data.\n  model.fit(xs, ys).then(() => {\n    \u002F\u002F Use the model to do inference on a data point the model hasn't seen before:\n    \u002F\u002F Open the browser devtools to see the output\n    model.predict(tf.tensor2d([5], [1, 1])).print();\n  });\n\u003C\u002Fscript>\n```\n\n## 更多资源\n\n- [官方文档](https:\u002F\u002Fjs.tensorflow.org\u002Fapi\u002Flatest\u002F)\n- [教程](https:\u002F\u002Fjs.tensorflow.org\u002Ftutorials)\n- [示例仓库](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs-examples)","某在线教育团队正在开发网页版电子白板，核心需求是在用户书写时实时识别手写数字并转换为文本。\n\n### 没有 tfjs 时\n- 必须将所有笔迹坐标上传到后端 Python 服务处理，网络延迟导致识别结果滞后，严重影响交互流畅度。\n- 涉及用户书写习惯等敏感数据外传，难以满足日益严格的数据隐私合规要求。\n- 高峰期并发请求量大，服务器 GPU 资源消耗巨大，运维成本居高不下。\n- 一旦网络波动或断开，整个识别功能立即失效，用户体验极差。\n\n### 使用 tfjs 后\n- 通过 WebGL 后端在浏览器端直接加载模型，推理速度提升至毫秒级，交互零延迟。\n- 模型转换后运行于客户端，原始数据不出本地，完美符合隐私保护规范。\n- 利用用户设备的 CPU 或 GPU 算力分担负载，显著降低了云端服务器的部署压力与成本。\n- 结合 Service Worker 缓存机制，即使断网也能调用本地模型进行基础识别，保障业务连续性。\n\ntfjs 通过将机器学习能力下沉至前端，实现了低延迟、低成本且安全可靠的智能交互体验。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ftensorflow_tfjs_84b9135e.png","tensorflow","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Ftensorflow_07ed5093.png","",null,"github-admin@tensorflow.org","http:\u002F\u002Fwww.tensorflow.org","https:\u002F\u002Fgithub.com\u002Ftensorflow",[80,84,88,92,96,100,104,108,112,116],{"name":81,"color":82,"percentage":83},"TypeScript","#3178c6",80.2,{"name":85,"color":86,"percentage":87},"JavaScript","#f1e05a",8.5,{"name":89,"color":90,"percentage":91},"C++","#f34b7d",4.5,{"name":93,"color":94,"percentage":95},"Python","#3572A5",3.8,{"name":97,"color":98,"percentage":99},"Starlark","#76d275",1.3,{"name":101,"color":102,"percentage":103},"HTML","#e34c26",0.9,{"name":105,"color":106,"percentage":107},"Shell","#89e051",0.5,{"name":109,"color":110,"percentage":111},"CSS","#663399",0.2,{"name":113,"color":114,"percentage":115},"Objective-C","#438eff",0,{"name":117,"color":118,"percentage":115},"Java","#b07219",19112,2024,"2026-04-10T17:47:41","Apache-2.0","未说明",{"notes":125,"python":123,"dependencies":126},"该工具为 JavaScript 库，主要运行在浏览器或 Node.js 环境中。硬件加速通过 WebGL、WebGPU 或 WASM 后端实现，不强制依赖 NVIDIA CUDA 环境。使用 NPM 安装时需配合构建工具（如 Webpack）。",[127,128,129,130],"@tensorflow\u002Ftfjs","Parcel","Webpack","Rollup",[14],[133,134,135,136,137,138,139,140,141,142],"deep-learning","typescript","webgl","javascript","machine-learning","neural-network","deep-neural-network","gpu-acceleration","wasm","web-assembly",47,"2026-03-27T02:49:30.150509","2026-04-11T18:30:16.869381",[147,152,156,160,165,169],{"id":148,"question_zh":149,"answer_zh":150,"source_url":151},2381,"在 M1\u002FMac 芯片上安装 TensorFlow.js Node 时出现 \"Unsupported system\" 错误怎么办？","这是因为缺少 darwin\u002Farm64 的预编译库。请确保使用的是支持 Apple Silicon 的 Node.js 版本（建议 Node 16 或更高版本）。解决方法包括：1. 确认终端运行模式为原生 ARM64；2. 删除现有的 node_modules 目录；3. 重新安装 tfjs-node。如果问题依旧，请检查是否使用了最新的 tfjs-node 版本。","https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fissues\u002F4514",{"id":153,"question_zh":154,"answer_zh":155,"source_url":151},2382,"安装 TensorFlow.js 时遇到 \"Unsupported platform: darwin_x86_32\" 错误是什么原因？","这通常意味着你正在 Rosetta 转译模式下运行终端（系统识别为 x86 架构）。请关闭终端，确保使用原生的 Apple Silicon 终端重新打开，然后删除 node_modules 目录并重新安装依赖。同时确保使用的 Node 和 npm 二进制文件也是针对 Apple Silicon 构建的。",{"id":157,"question_zh":158,"answer_zh":159,"source_url":151},2383,"如何调试 TensorFlow.js Node 安装过程中的具体失败点？","建议创建一个干净的 npm 包环境进行测试。首先运行 `npm i @tensorflow\u002Ftfjs-node` 看安装是否成功。然后在 Node 环境中尝试运行以下代码来验证功能：\n```js\nconst tf = require('@tensorflow\u002Ftfjs-node');\ntf.tensor1d([1,2,3]).add(tf.tensor1d([4,5,6])).print();\n```\n观察是在安装步骤、require() 步骤还是计算步骤报错，以便定位具体问题。",{"id":161,"question_zh":162,"answer_zh":163,"source_url":164},2384,"Windows 系统导入 @tensorflow\u002Ftfjs-node-gpu 时报错 \"The specified module could not be found\" 如何解决？","这是常见的 Windows 依赖缺失问题。请尝试以下步骤：1. 进入 `@tensorflow\u002Ftfjs-node-gpu` 模块目录；2. 运行 `node-pre-gyp rebuild` 命令（如果未安装需先 `npm install -g node-pre-gyp`）；3. 查看是否有编译错误。如果路径中包含空格也可能导致问题，请确保路径无空格。","https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fissues\u002F2003",{"id":166,"question_zh":167,"answer_zh":168,"source_url":164},2385,"运行 `node-pre-gyp rebuild` 后 tfjs-node-gpu 仍然无法导入，有什么临时修复方案？","如果重建后仍然提示找不到 `tfjs_binding.node` 或相关模块，可以尝试手动复制依赖文件。从旧版本的 Node 模块目录中复制 `tensorflow.dll` 文件到当前模块的对应路径下。例如，可以从 Node v10.16.3 的模块目录 (`node_modules\\@tensorflow\\tfjs-node\\lib\\napi-v4`) 复制 `tensorflow.dll` 到 Node 12 的对应模块目录中，这有时能解决模块加载问题。",{"id":170,"question_zh":171,"answer_zh":172,"source_url":164},2386,"Windows 上 tfjs-node-gpu 无法使用时，CPU 版本是否正常可用？","是的，根据社区反馈，即使 GPU 版本 (`tfjs-node-gpu`) 因环境配置问题无法工作，标准的 CPU 版本 (`@tensorflow\u002Ftfjs-node`) 通常可以正常运行。如果 GPU 加速暂时无法解决，可以先使用 CPU 版本进行开发测试，确保模型推理逻辑无误后再排查 GPU 环境配置。",[174,179,184,189,194,199,204,209,214,219,224,229,234,239,244,249,254,259,264,269],{"id":175,"version":176,"summary_zh":177,"released_at":178},200534,"tfjs-v4.22.0","## Core (4.21.0 ==> 4.22.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.22.0. ([#8419](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8419)). Thanks, @dbcp1.\r\n- Fix typos in the documentation strings of the tfjs-core directory ([#8413](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8413)). Thanks, @gaikwadrahul8.\r\n\r\n## Data (4.21.0 ==> 4.22.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.22.0. ([#8419](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8419)). Thanks, @dbcp1.\r\n- [tfjs-data] support async generator ([#8408](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8408)). Thanks, @tharvik.\r\n\r\n## Layers (4.21.0 ==> 4.22.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.22.0. ([#8419](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8419)). Thanks, @dbcp1.\r\n- Fix typos in the documentation strings of the tfjs-layers directory ([#8411](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8411)). Thanks, @gaikwadrahul8.\r\n\r\n## Converter (4.21.0 ==> 4.22.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.22.0_lockfiles lock files. ([#8420](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8420)). Thanks, @dbcp1.\r\n- Update monorepo to 4.22.0. ([#8419](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8419)). Thanks, @dbcp1.\r\n\r\n## Node (4.21.0 ==> 4.22.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.22.0_lockfiles lock files. ([#8420](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8420)). Thanks, @dbcp1.\r\n- Update monorepo to 4.22.0. ([#8419](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8419)). Thanks, @dbcp1.\r\n- Fix typos in the documentation strings of the tfjs-node directory ([#8412](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8412)). Thanks, @gaikwadrahul8.\r\n\r\n## Wasm (4.21.0 ==> 4.22.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.22.0_lockfiles lock files. ([#8420](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8420)). Thanks, @dbcp1.\r\n- Update monorepo to 4.22.0. ([#8419](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8419)). Thanks, @dbcp1.\r\n\r\n## Cpu (4.21.0 ==> 4.22.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.22.0. ([#8419](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8419)). Thanks, @dbcp1.\r\n\r\n## Webgl (4.21.0 ==> 4.22.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.22.0_lockfiles lock files. ([#8420](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8420)). Thanks, @dbcp1.\r\n- Update monorepo to 4.22.0. ([#8419](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8419)). Thanks, @dbcp1.\r\n\r\n## WebGPU (4.21.0 ==> 4.22.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.22.0_lockfiles lock files. ([#8420](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8420)). Thanks, @dbcp1.\r\n- Update monorepo to 4.22.0. ([#8419](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8419)). Thanks, @dbcp1.\r\n- webgpu: fix: conditionally call deprecated GPUAdapter.requestAdapterInfo ([#8392](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8392)). Thanks, @mattvr.","2024-10-21T21:21:13",{"id":180,"version":181,"summary_zh":182,"released_at":183},200535,"tfjs-v4.21.0","## Core (4.20.0 ==> 4.21.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.21.0. ([#8371](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8371)). Thanks, @dbcp1.\r\n- Update supported TypedArray data types in tf.tensor in the documentation ([#8287](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8287)). Thanks, @gaikwadrahul8.\r\n\r\n## Data (4.20.0 ==> 4.21.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.21.0. ([#8371](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8371)). Thanks, @dbcp1.\r\n\r\n## Layers (4.20.0 ==> 4.21.0)\r\n\r\n### Features\r\n- Subject: Add R2Score metric.  (#8353) ([#8169](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8169)). Thanks, @lukonik.\r\n### Misc\r\n- Update monorepo to 4.21.0. ([#8371](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8371)). Thanks, @dbcp1.\r\n- Fix iOS nightly device deprecated by updating device ([#8348](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8348)).\r\n\r\n## Converter (4.20.0 ==> 4.21.0)\r\n\r\n### Bug fixes\r\n- Quote props of DataType enum to prevent name mangling ([#8361](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8361)).\r\n### Misc\r\n- Update lockfiles branch tfjs_4.21.0_lockfiles lock files. ([#8372](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8372)). Thanks, @dbcp1.\r\n- Update monorepo to 4.21.0. ([#8371](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8371)). Thanks, @dbcp1.\r\n- Update broken link for tf.keras SavedModel in README.md ([#8313](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8313)). Thanks, @gaikwadrahul8.\r\n\r\n## Node (4.20.0 ==> 4.21.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.21.0_lockfiles lock files. ([#8372](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8372)). Thanks, @dbcp1.\r\n- Update monorepo to 4.21.0. ([#8371](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8371)). Thanks, @dbcp1.\r\n\r\n## Wasm (4.20.0 ==> 4.21.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.21.0_lockfiles lock files. ([#8372](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8372)). Thanks, @dbcp1.\r\n- Update monorepo to 4.21.0. ([#8371](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8371)). Thanks, @dbcp1.\r\n\r\n## Cpu (4.20.0 ==> 4.21.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.21.0. ([#8371](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8371)). Thanks, @dbcp1.\r\n\r\n## Webgl (4.20.0 ==> 4.21.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.21.0_lockfiles lock files. ([#8372](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8372)). Thanks, @dbcp1.\r\n- Update monorepo to 4.21.0. ([#8371](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8371)). Thanks, @dbcp1.\r\n\r\n## WebGPU (4.20.0 ==> 4.21.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.21.0_lockfiles lock files. ([#8372](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8372)). Thanks, @dbcp1.\r\n- Update monorepo to 4.21.0. ([#8371](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8371)). Thanks, @dbcp1.","2024-09-04T17:42:43",{"id":185,"version":186,"summary_zh":187,"released_at":188},200536,"tfjs-v4.20.0","## Core (4.19.0 ==> 4.20.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.20.0. ([#8294](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8294)). Thanks, @dbcp1.\r\n\r\n## Data (4.19.0 ==> 4.20.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.20.0. ([#8294](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8294)). Thanks, @dbcp1.\r\n\r\n## Layers (4.19.0 ==> 4.20.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.20.0. ([#8294](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8294)). Thanks, @dbcp1.\r\n\r\n## Converter (4.19.0 ==> 4.20.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.20.0_lockfiles lock files. ([#8296](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8296)). Thanks, @dbcp1.\r\n- Update monorepo to 4.20.0. ([#8294](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8294)). Thanks, @dbcp1.\r\n\r\n## Node (4.19.0 ==> 4.20.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.20.0_lockfiles lock files. ([#8296](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8296)). Thanks, @dbcp1.\r\n- Update monorepo to 4.20.0. ([#8294](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8294)). Thanks, @dbcp1.\r\n- Update tar package version for tfjs-node & tfjs-node-gpu ([#8280](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8280)). Thanks, @gaikwadrahul8.\r\n\r\n## Wasm (4.19.0 ==> 4.20.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.20.0_lockfiles lock files. ([#8296](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8296)). Thanks, @dbcp1.\r\n- Update monorepo to 4.20.0. ([#8294](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8294)). Thanks, @dbcp1.\r\n\r\n## Cpu (4.19.0 ==> 4.20.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.20.0. ([#8294](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8294)). Thanks, @dbcp1.\r\n\r\n## Webgl (4.19.0 ==> 4.20.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.20.0_lockfiles lock files. ([#8296](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8296)). Thanks, @dbcp1.\r\n- Update monorepo to 4.20.0. ([#8294](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8294)). Thanks, @dbcp1.\r\n\r\n## WebGPU (4.19.0 ==> 4.20.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.20.0_lockfiles lock files. ([#8296](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8296)). Thanks, @dbcp1.\r\n- Update monorepo to 4.20.0. ([#8294](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8294)). Thanks, @dbcp1.","2024-06-03T21:39:14",{"id":190,"version":191,"summary_zh":192,"released_at":193},200537,"tfjs-v4.19.0","## Core (4.18.0 ==> 4.19.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.19.0. ([#8263](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8263)). Thanks, @dbcp1.\r\n\r\n## Data (4.18.0 ==> 4.19.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.19.0. ([#8263](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8263)). Thanks, @dbcp1.\r\n\r\n## Layers (4.18.0 ==> 4.19.0)\r\n\r\n### Features\r\n- Add support for GELU and approximate activation functions ([#8224](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8224)). Thanks, @Vectorrent.\r\n### Bug fixes\r\n- Update exception logic in convolutional.ts ([#8248](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8248)). Thanks, @gaikwadrahul8.\r\n### Misc\r\n- Update monorepo to 4.19.0. ([#8263](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8263)). Thanks, @dbcp1.\r\n\r\n## Converter (4.18.0 ==> 4.19.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.19.0_lockfiles lock files. ([#8264](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8264)). Thanks, @dbcp1.\r\n- Update monorepo to 4.19.0. ([#8263](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8263)). Thanks, @dbcp1.\r\n\r\n## Node (4.18.0 ==> 4.19.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.19.0_lockfiles lock files. ([#8264](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8264)). Thanks, @dbcp1.\r\n- Update monorepo to 4.19.0. ([#8263](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8263)). Thanks, @dbcp1.\r\n- Update installation steps for Windows \u002F Mac OS X for tfjs-node in README.md ([#8101](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8101)). Thanks, @gaikwadrahul8.\r\n\r\n## Wasm (4.18.0 ==> 4.19.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.19.0_lockfiles lock files. ([#8264](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8264)). Thanks, @dbcp1.\r\n- Update monorepo to 4.19.0. ([#8263](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8263)). Thanks, @dbcp1.\r\n- Fixing typos in READMEs ([#8213](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8213)). Thanks, @Branchverse.\r\n\r\n## Cpu (4.18.0 ==> 4.19.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.19.0. ([#8263](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8263)). Thanks, @dbcp1.\r\n\r\n## Webgl (4.18.0 ==> 4.19.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.19.0_lockfiles lock files. ([#8264](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8264)). Thanks, @dbcp1.\r\n- Update monorepo to 4.19.0. ([#8263](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8263)). Thanks, @dbcp1.\r\n\r\n## WebGPU (4.18.0 ==> 4.19.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.19.0_lockfiles lock files. ([#8264](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8264)). Thanks, @dbcp1.\r\n- Update monorepo to 4.19.0. ([#8263](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8263)). Thanks, @dbcp1.\r\n- Export WebGPUProgram as type to fix g3 isolatedModules issue ([#8252](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8252)).","2024-04-30T21:25:12",{"id":195,"version":196,"summary_zh":197,"released_at":198},200538,"tfjs-v4.18.0","## Core (4.17.0 ==> 4.18.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.18.0. ([#8250](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8250)). Thanks, @dbcp1.\r\n\r\n## Data (4.17.0 ==> 4.18.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.18.0. ([#8250](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8250)). Thanks, @dbcp1.\r\n\r\n## Layers (4.17.0 ==> 4.18.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.18.0. ([#8250](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8250)). Thanks, @dbcp1.\r\n\r\n## Converter (4.17.0 ==> 4.18.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.18.0_lockfiles lock files. ([#8251](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8251)). Thanks, @dbcp1.\r\n- Update monorepo to 4.18.0. ([#8250](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8250)). Thanks, @dbcp1.\r\n- nightly test fix ([#8214](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8214)).\r\n- Fixed typos in documentation string. ([#7782](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7782)). Thanks, @shmishra99.\r\n\r\n## Node (4.17.0 ==> 4.18.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.18.0_lockfiles lock files. ([#8251](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8251)). Thanks, @dbcp1.\r\n- Update monorepo to 4.18.0. ([#8250](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8250)). Thanks, @dbcp1.\r\n\r\n## Wasm (4.17.0 ==> 4.18.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.18.0_lockfiles lock files. ([#8251](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8251)). Thanks, @dbcp1.\r\n- Update monorepo to 4.18.0. ([#8250](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8250)). Thanks, @dbcp1.\r\n\r\n## Cpu (4.17.0 ==> 4.18.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.18.0. ([#8250](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8250)). Thanks, @dbcp1.\r\n\r\n## Webgl (4.17.0 ==> 4.18.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.18.0_lockfiles lock files. ([#8251](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8251)). Thanks, @dbcp1.\r\n- Update monorepo to 4.18.0. ([#8250](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8250)). Thanks, @dbcp1.\r\n\r\n## WebGPU (4.17.0 ==> 4.18.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.18.0_lockfiles lock files. ([#8251](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8251)). Thanks, @dbcp1.\r\n- Update monorepo to 4.18.0. ([#8250](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8250)). Thanks, @dbcp1.","2024-04-17T22:18:02",{"id":200,"version":201,"summary_zh":202,"released_at":203},200539,"tfjs-v4.17.0","## Core (4.16.0 ==> 4.17.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.17.0. ([#8161](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8161)). Thanks, @dbcp1.\r\n\r\n## Data (4.16.0 ==> 4.17.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.17.0. ([#8161](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8161)). Thanks, @dbcp1.\r\n\r\n## Layers (4.16.0 ==> 4.17.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.17.0. ([#8161](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8161)). Thanks, @dbcp1.\r\n\r\n## Converter (4.16.0 ==> 4.17.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.17.0_lockfiles lock files. ([#8162](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8162)). Thanks, @dbcp1.\r\n- Update monorepo to 4.17.0. ([#8161](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8161)). Thanks, @dbcp1.\r\n- merge g3 cl ([#8138](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8138)).\r\n\r\n## Node (4.16.0 ==> 4.17.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.17.0_lockfiles lock files. ([#8162](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8162)). Thanks, @dbcp1.\r\n- Update monorepo to 4.17.0. ([#8161](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8161)). Thanks, @dbcp1.\r\n- Fix for windows installation #7341 ([#8122](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8122)). Thanks, @vicmmg.\r\n- Update broken link for MacOS Catalina guide in README.md ([#8032](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8032)). Thanks, @gaikwadrahul8.\r\n\r\n## Wasm (4.16.0 ==> 4.17.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.17.0_lockfiles lock files. ([#8162](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8162)). Thanks, @dbcp1.\r\n- Update monorepo to 4.17.0. ([#8161](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8161)). Thanks, @dbcp1.\r\n\r\n## Cpu (4.16.0 ==> 4.17.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.17.0. ([#8161](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8161)). Thanks, @dbcp1.\r\n\r\n## Webgl (4.16.0 ==> 4.17.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.17.0_lockfiles lock files. ([#8162](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8162)). Thanks, @dbcp1.\r\n- Update monorepo to 4.17.0. ([#8161](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8161)). Thanks, @dbcp1.\r\n\r\n## WebGPU (4.16.0 ==> 4.17.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.17.0_lockfiles lock files. ([#8162](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8162)). Thanks, @dbcp1.\r\n- Update monorepo to 4.17.0. ([#8161](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8161)). Thanks, @dbcp1.","2024-01-31T00:08:32",{"id":205,"version":206,"summary_zh":207,"released_at":208},200540,"tfjs-v4.16.0","## Core (4.15.0 ==> 4.16.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.16.0. ([#8136](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8136)). Thanks, @dbcp1.\r\n\r\n## Data (4.15.0 ==> 4.16.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.16.0. ([#8136](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8136)). Thanks, @dbcp1.\r\n\r\n## Layers (4.15.0 ==> 4.16.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.16.0. ([#8136](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8136)). Thanks, @dbcp1.\r\n\r\n## Converter (4.15.0 ==> 4.16.0)\r\n\r\n### Bug fixes\r\n- apply g3 fixes for jax ([#8099](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8099)).\r\n### Misc\r\n- Update lockfiles branch tfjs_4.16.0_lockfiles lock files. ([#8137](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8137)). Thanks, @dbcp1.\r\n- Update monorepo to 4.16.0. ([#8136](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8136)). Thanks, @dbcp1.\r\n- Add support for complex64 data type in `parseDtypeParam` function ([#8083](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8083)). Thanks, @Lutra-Fs.\r\n\r\n## Node (4.15.0 ==> 4.16.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.16.0_lockfiles lock files. ([#8137](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8137)). Thanks, @dbcp1.\r\n- Update monorepo to 4.16.0. ([#8136](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8136)). Thanks, @dbcp1.\r\n\r\n## Wasm (4.15.0 ==> 4.16.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.16.0_lockfiles lock files. ([#8137](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8137)). Thanks, @dbcp1.\r\n- Update monorepo to 4.16.0. ([#8136](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8136)). Thanks, @dbcp1.\r\n\r\n## Cpu (4.15.0 ==> 4.16.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.16.0. ([#8136](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8136)). Thanks, @dbcp1.\r\n\r\n## Webgl (4.15.0 ==> 4.16.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.16.0_lockfiles lock files. ([#8137](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8137)). Thanks, @dbcp1.\r\n- Update monorepo to 4.16.0. ([#8136](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8136)). Thanks, @dbcp1.\r\n\r\n## WebGPU (4.15.0 ==> 4.16.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.16.0_lockfiles lock files. ([#8137](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8137)). Thanks, @dbcp1.\r\n- Update monorepo to 4.16.0. ([#8136](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8136)). Thanks, @dbcp1.","2024-01-11T02:07:13",{"id":210,"version":211,"summary_zh":212,"released_at":213},200541,"tfjs-v4.15.0","## Core (4.14.0 ==> 4.15.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.15.0. ([#8096](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8096)). Thanks, @dbcp1.\r\n- Stream weights to the GPU when loading a model ([#7994](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7994)).\r\n\r\n## Data (4.14.0 ==> 4.15.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.15.0. ([#8096](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8096)). Thanks, @dbcp1.\r\n\r\n## Layers (4.14.0 ==> 4.15.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.15.0. ([#8096](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8096)). Thanks, @dbcp1.\r\n\r\n## Converter (4.14.0 ==> 4.15.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.15.0_lockfiles lock files. ([#8098](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8098)). Thanks, @dbcp1.\r\n- Update monorepo to 4.15.0. ([#8096](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8096)). Thanks, @dbcp1.\r\n- Stream weights to the GPU when loading a model ([#7994](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7994)).\r\n\r\n## Node (4.14.0 ==> 4.15.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.15.0_lockfiles lock files. ([#8098](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8098)). Thanks, @dbcp1.\r\n- Update monorepo to 4.15.0. ([#8096](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8096)). Thanks, @dbcp1.\r\n\r\n## Wasm (4.14.0 ==> 4.15.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.15.0_lockfiles lock files. ([#8098](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8098)). Thanks, @dbcp1.\r\n- Update monorepo to 4.15.0. ([#8096](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8096)). Thanks, @dbcp1.\r\n\r\n## Cpu (4.14.0 ==> 4.15.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.15.0. ([#8096](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8096)). Thanks, @dbcp1.\r\n\r\n## Webgl (4.14.0 ==> 4.15.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.15.0_lockfiles lock files. ([#8098](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8098)). Thanks, @dbcp1.\r\n- Update monorepo to 4.15.0. ([#8096](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8096)). Thanks, @dbcp1.\r\n\r\n## WebGPU (4.14.0 ==> 4.15.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.15.0_lockfiles lock files. ([#8098](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8098)). Thanks, @dbcp1.\r\n- Update monorepo to 4.15.0. ([#8096](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8096)). Thanks, @dbcp1.","2023-12-13T22:23:39",{"id":215,"version":216,"summary_zh":217,"released_at":218},200542,"tfjs-v4.14.0","## Core (4.13.0 ==> 4.14.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.14.0. ([#8085](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8085)).\r\n- webgpu: apply the new timestampWrites format ([#8048](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8048)). Thanks, @qjia7.\r\n- Fix worker tests using the wrong paths in importScripts ([#8050](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8050)).\r\n\r\n## Data (4.13.0 ==> 4.14.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.14.0. ([#8085](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8085)).\r\n\r\n## Layers (4.13.0 ==> 4.14.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.14.0. ([#8085](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8085)).\r\n\r\n## Converter (4.13.0 ==> 4.14.0)\r\n\r\n### Documentation\r\n- Update correct links for Keras HDF5 and tf.keras SavedModel in README.md ([#8051](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8051)). Thanks, @gaikwadrahul8.\r\n### Misc\r\n- Update lockfiles branch tfjs_4.14.0_lockfiles lock files. ([#8086](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8086)). Thanks, @dbcp1.\r\n- Update monorepo to 4.14.0. ([#8085](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8085)).\r\n- Update broken link for Frozen Model hyperlink in  README.md ([#8063](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8063)). Thanks, @gaikwadrahul8.\r\n\r\n## Node (4.13.0 ==> 4.14.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.14.0_lockfiles lock files. ([#8086](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8086)). Thanks, @dbcp1.\r\n- Update monorepo to 4.14.0. ([#8085](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8085)).\r\n\r\n## Wasm (4.13.0 ==> 4.14.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.14.0_lockfiles lock files. ([#8086](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8086)). Thanks, @dbcp1.\r\n- Update monorepo to 4.14.0. ([#8085](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8085)).\r\n\r\n## Cpu (4.13.0 ==> 4.14.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.14.0. ([#8085](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8085)).\r\n\r\n## Webgl (4.13.0 ==> 4.14.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.14.0_lockfiles lock files. ([#8086](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8086)). Thanks, @dbcp1.\r\n- Update monorepo to 4.14.0. ([#8085](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8085)).\r\n\r\n## WebGPU (4.13.0 ==> 4.14.0)\r\n\r\n### Bug fixes\r\n- Fix isWebGPUSupported throwing an error in node ([#8070](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8070)).\r\n### Misc\r\n- Update lockfiles branch tfjs_4.14.0_lockfiles lock files. ([#8086](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8086)). Thanks, @dbcp1.\r\n- Update monorepo to 4.14.0. ([#8085](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8085)).\r\n- webgpu: apply the new timestampWrites format ([#8048](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8048)). Thanks, @qjia7.","2023-11-30T20:34:44",{"id":220,"version":221,"summary_zh":222,"released_at":223},200543,"tfjs-react-native-v1.0.0","## tfjs-react-native (0.8.0 ==> 1.0.0)\r\n\r\nThis update fixes a lot of the old dependency version issues, including bringing the react native dependency up from 0.59.0 to 0.72.0. Thanks @paradite!\r\n\r\n### Features\r\n- Update tfjs-react-native dependencies ([#8062](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8062)). Thanks, @paradite.\r\n### Documentation\r\n- Remove step to install expo-gl-cpp ([#7286](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7286)). Thanks, @Rhysjc.\r\n### Security\r\n- build(deps): bump http-cache-semantics in \u002Ftfjs-react-native ([#7340](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7340)). Thanks, @dependabot[bot].\r\n- build(deps): bump decode-uri-component ([#7150](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7150)). Thanks, @dependabot[bot].\r\n- build(deps): bump qs in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#7149](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7149)). Thanks, @dependabot[bot].\r\n- Bump simple-plist in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#6485](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6485)). Thanks, @dependabot[bot].\r\n- Bump plist from 3.0.1 to 3.0.4 in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#6182](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6182)). Thanks, @dependabot[bot].\r\n### Misc\r\n- Update tfjs-react-native to 1.0.0. ([#8071](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8071)).\r\n- build(deps): bump semver in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#7820](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7820)). Thanks, @dependabot[bot].\r\n- Update vis, automl, inference, and react-native deps to tfjs 4.3.0 ([#7502](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7502)).\r\n- React native update tfjs to 4.2.0 ([#7451](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7451)).\r\n- build(deps): bump ua-parser-js in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#7319](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7319)). Thanks, @dependabot[bot].\r\n- build(deps): bump json5 from 2.2.0 to 2.2.3 in \u002Ftfjs-react-native ([#7241](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7241)). Thanks, @dependabot[bot].\r\n- build(deps): bump json5 in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#7238](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7238)). Thanks, @dependabot[bot].\r\n- Bump minimatch from 3.0.4 to 3.1.2 in \u002Ftfjs-react-native ([#7083](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7083)). Thanks, @dependabot[bot].\r\n- Bump minimatch in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#7080](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7080)). Thanks, @dependabot[bot].\r\n- fix: typo in error output ([#7002](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7002)). Thanks, @TGTGamer.\r\n- Add path mapping to the root tsconfig ([#6957](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6957)).\r\n- Upgrade tfjs repo to 4.0.0 ([#6927](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6927)).\r\n- Fixed the typo: cosnt -> const ([#6798](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6798)). Thanks, @I-am-vishalmaurya.\r\n- Bump jpeg-js from 0.4.3 to 0.4.4 in \u002Ftfjs-react-native ([#6547](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6547)). Thanks, @dependabot[bot].\r\n- Bump jpeg-js from 0.4.3 to 0.4.4 in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#6546](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6546)). Thanks, @dependabot[bot].\r\n- [secu] update package.json files to resolve security alerts ([#6448](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6448)).\r\n- Bump plist from 3.0.4 to 3.0.5 in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#6276](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6276)). Thanks, @dependabot[bot].\r\n- Bump ansi-regex from 4.1.0 to 4.1.1 in \u002Ftfjs-react-native ([#6275](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6275)). Thanks, @dependabot[bot].\r\n- Security fixes ([#6268](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6268)).\r\n- Bump lodash in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#6225](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6225)). Thanks, @dependabot[bot].\r\n- yarn.lock updates for security warning ([#6229](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6229)).\r\n- Bump url-parse in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#6181](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6181)). Thanks, @dependabot[bot].\r\n- Bump ua-parser-js in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#6142](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6142)). Thanks, @dependabot[bot].\r\n- Bump ajv from 6.10.2 to 6.12.6 in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#6141](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6141)). Thanks, @dependabot[bot].\r\n- Bump handlebars in \u002Ftfjs-react-native\u002Fintegration_rn59 ([#6140](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F6140)). Thanks, @dependabot[bot].\r\n- Update package.json to include the repository ([#5770](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F5770)). Thanks, @v-rr.(base)","2023-11-30T21:43:46",{"id":225,"version":226,"summary_zh":227,"released_at":228},200544,"tfjs-v4.13.0","## Core (4.12.0 ==> 4.13.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.13.0. ([#8054](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8054)).\r\n- feat: fix tensor class import ([#7947](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7947)). Thanks, @paradite.\r\n\r\n## Data (4.12.0 ==> 4.13.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.13.0. ([#8054](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8054)).\r\n\r\n## Layers (4.12.0 ==> 4.13.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.13.0. ([#8054](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8054)).\r\n- [tfjs-layers] Fix outputs and mask mismatch ([#7993](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7993)). Thanks, @axinging.\r\n\r\n## Converter (4.12.0 ==> 4.13.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.13.0. ([#8054](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8054)).\r\n\r\n## Node (4.12.0 ==> 4.13.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.13.0. ([#8054](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8054)).\r\n\r\n## Wasm (4.12.0 ==> 4.13.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.13.0. ([#8054](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8054)).\r\n\r\n## Cpu (4.12.0 ==> 4.13.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.13.0. ([#8054](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8054)).\r\n\r\n## Webgl (4.12.0 ==> 4.13.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.13.0. ([#8054](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8054)).\r\n\r\n## WebGPU (4.12.0 ==> 4.13.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.13.0. ([#8054](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8054)).\r\n- fix browser check ([#8001](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8001)). Thanks, @crowlKats.","2023-11-09T18:27:49",{"id":230,"version":231,"summary_zh":232,"released_at":233},200545,"tfjs-v4.13.0-rc.0","## Core (4.12.0 ==> 4.13.0-rc.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.13.0-rc.0_lockfiles lock files. ([#8046](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8046)).\r\n- Update monorepo to 4.13.0-rc.0. ([#8043](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8043)).\r\n- feat: fix tensor class import ([#7947](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7947)). Thanks, @paradite.\r\n\r\n## Data (4.12.0 ==> 4.13.0-rc.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.13.0-rc.0. ([#8043](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8043)).\r\n\r\n## Layers (4.12.0 ==> 4.13.0-rc.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.13.0-rc.0. ([#8043](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8043)).\r\n- [tfjs-layers] Fix outputs and mask mismatch ([#7993](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7993)). Thanks, @axinging.\r\n\r\n## Converter (4.12.0 ==> 4.13.0-rc.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.13.0-rc.0_lockfiles lock files. ([#8046](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8046)).\r\n- Update monorepo to 4.13.0-rc.0. ([#8043](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8043)).\r\n\r\n## Node (4.12.0 ==> 4.13.0-rc.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.13.0-rc.0_lockfiles lock files. ([#8046](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8046)).\r\n- Update monorepo to 4.13.0-rc.0. ([#8043](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8043)).\r\n\r\n## Wasm (4.12.0 ==> 4.13.0-rc.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.13.0-rc.0_lockfiles lock files. ([#8046](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8046)).\r\n- Update monorepo to 4.13.0-rc.0. ([#8043](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8043)).\r\n\r\n## Cpu (4.12.0 ==> 4.13.0-rc.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.13.0-rc.0. ([#8043](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8043)).\r\n\r\n## Webgl (4.12.0 ==> 4.13.0-rc.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.13.0-rc.0_lockfiles lock files. ([#8046](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8046)).\r\n- Update monorepo to 4.13.0-rc.0. ([#8043](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8043)).\r\n\r\n## WebGPU (4.12.0 ==> 4.13.0-rc.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.13.0-rc.0_lockfiles lock files. ([#8046](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8046)).\r\n- Update monorepo to 4.13.0-rc.0. ([#8043](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8043)).\r\n- fix browser check ([#8001](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8001)). Thanks, @crowlKats.","2023-10-31T04:12:41",{"id":235,"version":236,"summary_zh":237,"released_at":238},200546,"tfjs-v4.12.0","## Core (4.11.0 ==> 4.12.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.12.0_lockfiles lock files. ([#8017](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8017)).\r\n- Update monorepo to 4.12.0. ([#8013](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8013)).\r\n\r\n## Data (4.11.0 ==> 4.12.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.12.0. ([#8013](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8013)).\r\n\r\n## Layers (4.11.0 ==> 4.12.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.12.0. ([#8013](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8013)).\r\n- [layers] Import arraysEqual from the public import path ([#7959](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7959)).\r\n\r\n## Converter (4.11.0 ==> 4.12.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.12.0_lockfiles lock files. ([#8017](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8017)).\r\n- Update monorepo to 4.12.0. ([#8013](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8013)).\r\n- [converter] fixed py import for auto tracking ([#7982](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7982)).\r\n\r\n## Node (4.11.0 ==> 4.12.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.12.0_lockfiles lock files. ([#8017](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8017)).\r\n- Update monorepo to 4.12.0. ([#8013](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8013)).\r\n- [converter] fixed py import for auto tracking ([#7982](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7982)).\r\n\r\n## Wasm (4.11.0 ==> 4.12.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.12.0_lockfiles lock files. ([#8017](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8017)).\r\n- Update monorepo to 4.12.0. ([#8013](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8013)).\r\n- Update broken link for Benchmarks page ([#7796](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7796)). Thanks, @gaikwadrahul8.\r\n- Infer dtype in wasm fill ([#7953](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7953)). Thanks, @sklum.\r\n\r\n## Cpu (4.11.0 ==> 4.12.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.12.0. ([#8013](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8013)).\r\n\r\n## Webgl (4.11.0 ==> 4.12.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.12.0_lockfiles lock files. ([#8017](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8017)).\r\n- Update monorepo to 4.12.0. ([#8013](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8013)).\r\n\r\n## WebGPU (4.11.0 ==> 4.12.0)\r\n\r\n### Bug fixes\r\n- webgpu: Enable importExternalTexture ([#7976](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7976)). Thanks, @gyagp.\r\n### Misc\r\n- Update lockfiles branch tfjs_4.12.0_lockfiles lock files. ([#8017](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8017)).\r\n- Update monorepo to 4.12.0. ([#8013](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F8013)).\r\n- [WebGPU] Fix shader key for ScatterProgram ([#7932](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7932)).","2023-10-18T18:19:38",{"id":240,"version":241,"summary_zh":242,"released_at":243},200547,"tfjs-v4.12.0-rc.0","## Core (4.11.0 ==> 4.12.0-rc.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.12.0-rc.0. ([#7998](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7998)). Thanks, @Dedongala.\r\n\r\n## Data (4.11.0 ==> 4.12.0-rc.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.12.0-rc.0. ([#7998](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7998)). Thanks, @Dedongala.\r\n\r\n## Layers (4.11.0 ==> 4.12.0-rc.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.12.0-rc.0. ([#7998](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7998)). Thanks, @Dedongala.\r\n- [layers] Import arraysEqual from the public import path ([#7959](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7959)).\r\n\r\n## Converter (4.11.0 ==> 4.12.0-rc.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.12.0-rc.0. ([#7998](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7998)). Thanks, @Dedongala.\r\n- [converter] fixed py import for auto tracking ([#7982](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7982)).\r\n\r\n## Node (4.11.0 ==> 4.12.0-rc.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.12.0-rc.0. ([#7998](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7998)). Thanks, @Dedongala.\r\n- [converter] fixed py import for auto tracking ([#7982](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7982)).\r\n\r\n## Wasm (4.11.0 ==> 4.12.0-rc.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.12.0-rc.0. ([#7998](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7998)). Thanks, @Dedongala.\r\n- Update broken link for Benchmarks page ([#7796](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7796)). Thanks, @gaikwadrahul8.\r\n- Infer dtype in wasm fill ([#7953](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7953)). Thanks, @sklum.\r\n\r\n## Cpu (4.11.0 ==> 4.12.0-rc.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.12.0-rc.0. ([#7998](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7998)). Thanks, @Dedongala.\r\n\r\n## Webgl (4.11.0 ==> 4.12.0-rc.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.12.0-rc.0. ([#7998](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7998)). Thanks, @Dedongala.\r\n\r\n## WebGPU (4.11.0 ==> 4.12.0-rc.0)\r\n\r\n### Bug fixes\r\n- webgpu: Enable importExternalTexture ([#7976](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7976)). Thanks, @gyagp.\r\n### Misc\r\n- Update monorepo to 4.12.0-rc.0. ([#7998](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7998)). Thanks, @Dedongala.\r\n- [WebGPU] Fix shader key for ScatterProgram ([#7932](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7932))","2023-10-13T20:22:26",{"id":245,"version":246,"summary_zh":247,"released_at":248},200548,"tfjs-v4.11.0","## Core (4.10.0 ==> 4.11.0)\r\n\r\n### Bug fixes\r\n- Make MultiHeadAttention use masks from query and value tensors ([#7951](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7951)).\r\n- [tfjs-core] fix gather gradient when batchDims is 1 ([#7942](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7942)). Thanks, @paradite.\r\n### Misc\r\n- Update lockfiles branch tfjs_4.11.0_lockfiles lock files. ([#7958](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7958)). Thanks, @Dedongala.\r\n- Update monorepo to 4.11.0. ([#7957](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7957)). Thanks, @Dedongala.\r\n- Re-enable nightly firefox tests ([#7954](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7954)).\r\n- [WebGPU] Ensure tf.any and tf.all return bool tensors ([#7928](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7928)).\r\n- [tfjs-node] fixed range issue for int32 tensor with size larger than 2 ^ 24 ([#7931](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7931)).\r\n- Disable firefox browserstack tests temporarily ([#7935](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7935)).\r\n\r\n## Data (4.10.0 ==> 4.11.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.11.0. ([#7957](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7957)). Thanks, @Dedongala.\r\n- Disable firefox browserstack tests temporarily ([#7935](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7935)).\r\n\r\n## Layers (4.10.0 ==> 4.11.0)\r\n\r\n### Bug fixes\r\n- Make MultiHeadAttention use masks from query and value tensors ([#7951](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7951)).\r\n### Misc\r\n- Update monorepo to 4.11.0. ([#7957](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7957)). Thanks, @Dedongala.\r\n- Re-enable nightly firefox tests ([#7954](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7954)).\r\n- Add spec for GPT2CausalLM and dependencies ([#7897](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7897)). Thanks, @pforderique.\r\n- Disable firefox browserstack tests temporarily ([#7935](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7935)).\r\n- Fix bug where a model with empty weights fails to load ([#7868](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7868)). Thanks, @thekevinscott.\r\n- Implement GPT2 Backbone ([#7894](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7894)). Thanks, @pforderique.\r\n- Implement TransformerDecoder layer ([#7890](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7890)). Thanks, @pforderique.\r\n- Implement CachedMultiHeadAttention layer ([#7882](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7882)). Thanks, @pforderique.\r\n- Implement PositionEmbedding layer ([#7887](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7887)). Thanks, @pforderique.\r\n- Implement MultiHeadAttention Layer ([#7875](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7875)). Thanks, @pforderique.\r\n- Update weights loading ([#7872](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7872)).\r\n\r\n## Converter (4.10.0 ==> 4.11.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.11.0_lockfiles lock files. ([#7958](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7958)). Thanks, @Dedongala.\r\n- Update monorepo to 4.11.0. ([#7957](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7957)). Thanks, @Dedongala.\r\n- Update Hyperlinks To Correct Hyperlinks ([#7891](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7891)). Thanks, @gaikwadrahul8.\r\n- Update README.md for tf-nightly-cpu-2.0-preview hyperlink ([#7879](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7879)). Thanks, @gaikwadrahul8.\r\n- fix converter tests ([#7901](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7901)).\r\n- [e2e] fix tf1 hashtable test ([#7904](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7904)).\r\n- Load python rules in tfjs-converter converters dir ([#7892](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7892)).\r\n- Strip debug ops in jax conversion tests ([#7889](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7889)).\r\n\r\n## Node (4.10.0 ==> 4.11.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.11.0_lockfiles lock files. ([#7958](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7958)). Thanks, @Dedongala.\r\n- Update monorepo to 4.11.0. ([#7957](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7957)). Thanks, @Dedongala.\r\n- [tfjs-node] fixed range issue for int32 tensor with size larger than 2 ^ 24 ([#7931](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7931)).\r\n\r\n## Wasm (4.10.0 ==> 4.11.0)\r\n\r\n### Bug fixes\r\n- fix wasm backend memory leak issue. ([#7915](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7915)). Thanks, @LiujhDev.\r\n### Misc\r\n- Update lockfiles branch tfjs_4.11.0_lockfiles lock files. ([#7958](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7958)). Thanks, @Dedongala.\r\n- Update monorepo to 4.11.0. ([#7957](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7957)). Thanks, @Dedongala.\r\n- Re-enable nightly firefox tests ([#7954](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7954)).\r\n- Disable firefox browserstack tests temporarily ([#7935](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7935)).\r\n\r\n## Cpu (4.10.0 ==> 4.11.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.11.0. ([#7957](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7957)). Thanks, @Dedongala.\r\n\r\n## Webgl (4.10.0 ==> 4.11.0)\r\n\r\n### Features\r\n- add flag ([#7934](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7934)).\r\n### Misc\r\n- Update lockfiles branch tfjs_4.11.0_lockfiles lock files. ([#7958]","2023-09-13T18:50:31",{"id":250,"version":251,"summary_zh":252,"released_at":253},200549,"tfjs-v4.10.0","## Core (4.9.0 ==> 4.10.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.10.0_lockfiles lock files. ([#7886](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7886)). Thanks, @Dedongala.\r\n- Update monorepo to 4.10.0. ([#7885](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7885)). Thanks, @Dedongala.\r\n- Avoid nextFrame test if precision is not enough ([#7845](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7845)).\r\n- Update TypeScript to 5.0.4 ([#7681](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7681)).\r\n\r\n## Data (4.9.0 ==> 4.10.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.10.0. ([#7885](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7885)). Thanks, @Dedongala.\r\n\r\n## Layers (4.9.0 ==> 4.10.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.10.0. ([#7885](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7885)). Thanks, @Dedongala.\r\n- Remove 0 epsilon ([#7883](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7883)). Thanks, @pforderique.\r\n- Add sliceUpdate util ([#7876](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7876)). Thanks, @pforderique.\r\n- Implement EinsumDense layer ([#7860](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7860)). Thanks, @pforderique.\r\n- Add expectTensorsNotClose ([#7871](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7871)). Thanks, @pforderique.\r\n- [gpt2bb spec] TransformerDecoder ([#7842](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7842)). Thanks, @pforderique.\r\n- [gpt2pre 4] GPT2Preprocessor Layer ([#7814](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7814)). Thanks, @pforderique.\r\n- Update TypeScript to 5.0.4 ([#7681](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7681)).\r\n- [gpt2pre 3] Preprocessor Layer ([#7794](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7794)). Thanks, @pforderique.\r\n\r\n## Converter (4.9.0 ==> 4.10.0)\r\n\r\n### Documentation\r\n- Support custom model conversion ([#7848](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7848)).\r\n### Misc\r\n- Update lockfiles branch tfjs_4.10.0_lockfiles lock files. ([#7886](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7886)). Thanks, @Dedongala.\r\n- Update monorepo to 4.10.0. ([#7885](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7885)). Thanks, @Dedongala.\r\n- fix the h5 conversion test ([#7861](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7861)).\r\n- fix the tests ([#7873](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7873)).\r\n- Update TypeScript to 5.0.4 ([#7681](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7681)).\r\n\r\n## Node (4.9.0 ==> 4.10.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.10.0_lockfiles lock files. ([#7886](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7886)). Thanks, @Dedongala.\r\n- Update monorepo to 4.10.0. ([#7885](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7885)). Thanks, @Dedongala.\r\n- Build node addon before running tests ([#7884](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7884)).\r\n- Update TypeScript to 5.0.4 ([#7681](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7681)).\r\n\r\n## Wasm (4.9.0 ==> 4.10.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.10.0_lockfiles lock files. ([#7886](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7886)). Thanks, @Dedongala.\r\n- Update monorepo to 4.10.0. ([#7885](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7885)). Thanks, @Dedongala.\r\n\r\n## Cpu (4.9.0 ==> 4.10.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.10.0. ([#7885](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7885)). Thanks, @Dedongala.\r\n\r\n## Webgl (4.9.0 ==> 4.10.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.10.0_lockfiles lock files. ([#7886](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7886)). Thanks, @Dedongala.\r\n- Update monorepo to 4.10.0. ([#7885](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7885)). Thanks, @Dedongala.\r\n- Update TypeScript to 5.0.4 ([#7681](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7681)).\r\n\r\n## WebGPU (4.9.0 ==> 4.10.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.10.0_lockfiles lock files. ([#7886](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7886)). Thanks, @Dedongala.\r\n- Update monorepo to 4.10.0. ([#7885](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7885)). Thanks, @Dedongala.","2023-08-01T20:27:30",{"id":255,"version":256,"summary_zh":257,"released_at":258},200550,"tfjs-tflite-v0.0.1-alpha.10","## tfjs-tflite (0.0.1-alpha.9 ==> 0.0.1-alpha.10)\r\n\r\n### Misc\r\n- Update tfjs-tflite to 0.0.1-alpha.10. ([#7870](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7870)). Thanks, @Dedongala.\r\n- Update TypeScript to 5.0.4 ([#7681](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7681)).\r\n- Update TypeScript to 4.9.4 ([#7300](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7300)).\r\n- build(deps): bump json5 from 2.2.0 to 2.2.3 in \u002Ftfjs-tflite\u002Fdemo ([#7237](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7237)). Thanks, @dependabot[bot].\r\n- Switch from android 9 to 10 for tests ([#7132](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7132)).\r\n- Load tflite and tfdf wasm files with http_archive ([#7124](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7124)).\r\n- Bump minimatch from 3.0.4 to 3.1.2 in \u002Ftfjs-tflite\u002Fdemo ([#7079](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7079)). Thanks, @dependabot[bot].\r\n- Turn on the `noImplicitOverride` tsconfig option ([#7009](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7009)).\r\n- Cleanup and standardize package.json scripts of Bazel packages ([#7005](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7005)).\r\n","2023-07-24T18:01:12",{"id":260,"version":261,"summary_zh":262,"released_at":263},200551,"tfjs-v4.9.0","## Core (4.8.0 ==> 4.9.0)\r\n\r\n### Features\r\n- [webgpu] Implement draw API ([#7749](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7749)). Thanks, @axinging.\r\n### Bug fixes\r\n- Increase epsilon values for draw tests ([#7841](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7841)).\r\n### Misc\r\n- Update monorepo to 4.9.0. ([#7850](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7850)). Thanks, @Dedongala.\r\n- RGB to grayscale for tf.image ([#7840](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7840)). Thanks, @yiyihg.\r\n- Update draw_test.ts ([#7836](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7836)).\r\n- Test floorDiv() against float32 inputs ([#7809](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7809)). Thanks, @hujiajie.\r\n\r\n## Data (4.8.0 ==> 4.9.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.9.0. ([#7850](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7850)). Thanks, @Dedongala.\r\n- Update tf.data hyperlink in README.md ([#7777](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7777)). Thanks, @gaikwadrahul8.\r\n\r\n## Layers (4.8.0 ==> 4.9.0)\r\n\r\n### Documentation\r\n- [Layers] Update weights loading for keras v3. ([#7761](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7761)).\r\n### Misc\r\n- Update monorepo to 4.9.0. ([#7850](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7850)). Thanks, @Dedongala.\r\n- [gpt2bb impl] Backbone class (1\u002F1) ([#7838](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7838)). Thanks, @pforderique.\r\n- [gpt2bb spec] PositionEmedding layer ([#7839](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7839)). Thanks, @pforderique.\r\n- Move tensor to array functions to utils ([#7810](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7810)). Thanks, @pforderique.\r\n- Use regex instead of sets to remove \u002Fg ([#7785](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7785)).\r\n- Add GPT2 Tokenizer and tests ([#7806](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7806)). Thanks, @pforderique.\r\n- [gpt2pre 1.2] Start End Packer call method ([#7791](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7791)). Thanks, @pforderique.\r\n- [gpt2pre 1.1] Start End Packer Base class ([#7790](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7790)). Thanks, @pforderique.\r\n- BPE Detokenize ([#7788](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7788)). Thanks, @pforderique.\r\n- [BPE PR 2.5] BytePairTokenizer tokenize function. ([#7780](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7780)). Thanks, @pforderique.\r\n- [BPE PR 2.4] BPE Class + Merge utilities ([#7774](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7774)). Thanks, @pforderique.\r\n- [BPE PR 2.2] All BPE Utils ([#7770](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7770)). Thanks, @pforderique.\r\n- Polyfill string.matchAll to unblock #7770 ([#7776](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7776)).\r\n- [BPE PR 2.1] BPE Utils ([#7760](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7760)). Thanks, @pforderique.\r\n\r\n## Converter (4.8.0 ==> 4.9.0)\r\n\r\n### Performance\r\n- [Model conversion tool] Support fusing Conv+Add ([#7799](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7799)).\r\n### Documentation\r\n- [Converter] Support Keras V3 Conversion ([#7691](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7691)).\r\n### Misc\r\n- Update lockfiles branch tfjs_4.9.0_lockfiles lock files. ([#7855](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7855)). Thanks, @Dedongala.\r\n- Update monorepo to 4.9.0. ([#7850](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7850)). Thanks, @Dedongala.\r\n- build(deps-dev): bump protobufjs from 6.11.3 to 7.2.4 in \u002Ftfjs-converter ([#7812](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7812)). Thanks, @dependabot[bot].\r\n- Update README.md ([#7762](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7762)). Thanks, @gaikwadrahul8.\r\n- Update README.md ([#7763](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7763)). Thanks, @gaikwadrahul8.\r\n- [Converter] Script for building the map ([#7732](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7732)).\r\n\r\n## Node (4.8.0 ==> 4.9.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.9.0_lockfiles lock files. ([#7855](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7855)). Thanks, @Dedongala.\r\n- Update monorepo to 4.9.0. ([#7850](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7850)). Thanks, @Dedongala.\r\n\r\n## Wasm (4.8.0 ==> 4.9.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.9.0_lockfiles lock files. ([#7855](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7855)). Thanks, @Dedongala.\r\n- Update monorepo to 4.9.0. ([#7850](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7850)). Thanks, @Dedongala.\r\n\r\n## Cpu (4.8.0 ==> 4.9.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.9.0. ([#7850](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7850)). Thanks, @Dedongala.\r\n\r\n## Webgl (4.8.0 ==> 4.9.0)\r\n\r\n### Features\r\n- [webgpu] Implement draw API ([#7749](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7749)). Thanks, @axinging.\r\n### Misc\r\n- Update lockfiles branch tfjs_4.9.0_lockfiles lock files. ([#7855](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7855)). Thanks, @Dedongala.\r\n- Update monorepo to 4.9.0. ([#7850](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7850)). Thanks, @Dedongala.\r\n- Test floorDiv() against float32 inputs ([#7809](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7809)). Thanks, @hujiajie.\r\n\r\n## WebGPU (4.8.0 ==> 4.9.0)\r\n\r\n### Features\r\n- [webgp","2023-07-19T19:42:21",{"id":265,"version":266,"summary_zh":267,"released_at":268},200552,"tfjs-v4.8.0","## Core (4.7.0 ==> 4.8.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.8.0. ([#7766](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7766)). Thanks, @Dedongala.\r\n- Avoid draw API warning if the current backend does not have implementation ([#7744](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7744)).\r\n- Add register name when register the class object ([#7717](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7717)).\r\n\r\n## Data (4.7.0 ==> 4.8.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.8.0. ([#7766](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7766)). Thanks, @Dedongala.\r\n\r\n## Layers (4.7.0 ==> 4.8.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.8.0. ([#7766](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7766)). Thanks, @Dedongala.\r\n- Add Tokenizer base class. ([#7757](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7757)). Thanks, @pforderique.\r\n\r\n## Converter (4.7.0 ==> 4.8.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.8.0_lockfiles lock files. ([#7769](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7769)). Thanks, @Dedongala.\r\n- Update monorepo to 4.8.0. ([#7766](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7766)). Thanks, @Dedongala.\r\n\r\n## Node (4.7.0 ==> 4.8.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.8.0_lockfiles lock files. ([#7769](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7769)). Thanks, @Dedongala.\r\n- Update monorepo to 4.8.0. ([#7766](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7766)). Thanks, @Dedongala.\r\n\r\n## Wasm (4.7.0 ==> 4.8.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.8.0_lockfiles lock files. ([#7769](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7769)). Thanks, @Dedongala.\r\n- Update monorepo to 4.8.0. ([#7766](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7766)). Thanks, @Dedongala.\r\n\r\n## Cpu (4.7.0 ==> 4.8.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.8.0. ([#7766](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7766)). Thanks, @Dedongala.\r\n\r\n## Webgl (4.7.0 ==> 4.8.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.8.0_lockfiles lock files. ([#7769](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7769)). Thanks, @Dedongala.\r\n- Update monorepo to 4.8.0. ([#7766](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7766)). Thanks, @Dedongala.\r\n\r\n## WebGPU (4.7.0 ==> 4.8.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.8.0_lockfiles lock files. ([#7769](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7769)). Thanks, @Dedongala.\r\n- Update monorepo to 4.8.0. ([#7766](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7766)). Thanks, @Dedongala.\r\n- webgpu: Refactor some helper functions of matmul\u002Fconv2d ([#7748](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7748)). Thanks, @qjia7.\r\n- [WebGPU] support SparseSegmentSum and SparseSegmentMean ([#7746](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7746)). Thanks, @xhcao.\r\n- webgpu: Delete benchmark_ops_test file ([#7747](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7747)). Thanks, @qjia7.\r\n- webgpu: Tighten the condition to go the plain argminmax ([#7742](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7742)). Thanks, @qjia7.\r\n- [webgpu] Update ELU_DER ([#7745](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7745)). Thanks, @hujiajie.\r\n- [webgpu] Update ATAN2,MAX,MIN ([#7743](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7743)). Thanks, @hujiajie.\r\n- [webgpu] Update ADD,COMPLEX_MULTIPLY_*,DIV,MUL,SQUARED_DIFFERENCE,SUB ([#7737](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7737)). Thanks, @hujiajie.dedongala@d","2023-06-22T00:51:53",{"id":270,"version":271,"summary_zh":272,"released_at":273},200553,"tfjs-v4.7.0","## Core (4.6.0 ==> 4.7.0)\r\n\r\n### Documentation\r\n- Improve the code snippet for texture to tensor ([#7694](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7694)).\r\n### Misc\r\n- Update monorepo to 4.7.0. ([#7740](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7740)). Thanks, @Dedongala.\r\n- Fix indexeddb for 1GB models ([#7725](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7725)).\r\n- webgpu: Replace timestamp-query-in-passes with timestamp-query ([#7714](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7714)). Thanks, @gyagp.\r\n- Recover the default backend ([#7709](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7709)). Thanks, @qjia7.\r\n- [wasm] Fix cos and tan for large float numbers ([#7689](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7689)).\r\n\r\n## Data (4.6.0 ==> 4.7.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.7.0. ([#7740](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7740)). Thanks, @Dedongala.\r\n\r\n## Layers (4.6.0 ==> 4.7.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.7.0. ([#7740](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7740)). Thanks, @Dedongala.\r\n- Fix getLayer() API ([#7665](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7665)).\r\n\r\n## Converter (4.6.0 ==> 4.7.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.7.0_lockfiles lock files. ([#7741](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7741)). Thanks, @Dedongala.\r\n- Update monorepo to 4.7.0. ([#7740](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7740)). Thanks, @Dedongala.\r\n\r\n## Node (4.6.0 ==> 4.7.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.7.0_lockfiles lock files. ([#7741](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7741)). Thanks, @Dedongala.\r\n- Update monorepo to 4.7.0. ([#7740](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7740)). Thanks, @Dedongala.\r\n- [wasm] Fix cos and tan for large float numbers ([#7689](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7689)).\r\n\r\n## Wasm (4.6.0 ==> 4.7.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.7.0_lockfiles lock files. ([#7741](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7741)). Thanks, @Dedongala.\r\n- Update monorepo to 4.7.0. ([#7740](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7740)). Thanks, @Dedongala.\r\n- Revert \"[wasm] Update xnnpack \" (#7735) ([#7507](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7507)).\r\n- [wasm] Update xnnpack ([#7507](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7507)).\r\n- [wasm] Fix cos and tan for large float numbers ([#7689](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7689)).\r\n\r\n## Cpu (4.6.0 ==> 4.7.0)\r\n\r\n### Misc\r\n- Update monorepo to 4.7.0. ([#7740](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7740)). Thanks, @Dedongala.\r\n\r\n## Webgl (4.6.0 ==> 4.7.0)\r\n\r\n### Misc\r\n- Update lockfiles branch tfjs_4.7.0_lockfiles lock files. ([#7741](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7741)). Thanks, @Dedongala.\r\n- Update monorepo to 4.7.0. ([#7740](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7740)). Thanks, @Dedongala.\r\n- [wasm] Fix cos and tan for large float numbers ([#7689](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Ftfjs\u002Fpull\u002F7689)).","2023-06-06T20:56:00"]