TensorFlow五周年，官方发布“庆祝指南”

{"type":"doc","content":[{"type":"blockquote","content":[{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"2015年，谷歌开源了用于研究和生产的机器学习框架——TensorFlow，如今它已经走过了五年，并且成为最流行的机器学习框架之一。在 TensorFlow 五周年之际，谷歌官网发布了一篇文章来为它庆生。"}]}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"五年前，我们开源了 TensorFlow，这是我们用于研究和生产的一款机器学习框架。我们的目标是让任何人都可以用到最先进的机器学习工具。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"从那时起，TensorFlow 已经成为世界上最受欢迎的机器学习库，下载量超过 1.6 亿次。看到这么多人使用 TensorFlow 让我们感到有些难以置信、羞愧难当。感谢世界各地数以千计的非谷歌人士，他们贡献过代码、创建过教育课程、组织过开发活动，为 TensorFlow 和不断壮大的机器学习社区提供了大力支持。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"为庆祝 TensorFlow 诞生五周年，我们提供了一些交互演示，在浏览器中点点鼠标即可进行尝试，还有一些可以帮助你创建自己的项目的教程。如果你刚刚接触 TensorFlow，这是了解它的功能的一个绝佳方法。如果你喜欢这些内容，想要进一步深入了解，请浏览 TensorFlow 的博客。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"heading","attrs":{"align":null,"level":3},"content":[{"type":"text","text":"试试由机器学习驱动的交互式演示"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"TensorFlow 支持多种编程语言和环境。我们先来看一个 JavaScript 的快速展览，以及三个只需单击鼠标即可尝试的交互式演示。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"TensorFlow.js 允许你完全在浏览器中编写和运行机器学习模型。这对于隐私保护应用程序 (不需要将数据发送到服务器) 和交互式机器学习程序都有重要的意义。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"iris 的地标跟踪程序 是一个很好的例子，它支持免手动接口和辅助技术；你可以在你的浏览器中自己尝试这个模型 (耐心等待一会儿，可能需要一些时间加载！)"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"image","attrs":{"src":"https:\/\/mmbiz.qpic.cn\/mmbiz_gif\/ZBjVrHIdkOkicoxcgJztpETp6Faic7iaAR2KACNe2GG6kicpPibKDgkBq7D9aica18lW12zGKicbrhtVl1rmVAibopVvIQ\/640?wx_fmt=gif&tp=webp&wxfrom=5&wx_lazy=1","alt":null,"title":null,"style":null,"href":null,"fromPaste":true,"pastePass":false}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":"center","origin":null},"content":[{"type":"text","text":"动画演示软件通过分析虹膜来进行跟踪"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"与眼球跟踪类似，你也可以使用 TensorFlow.js 来跟踪 手部运动。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"image","attrs":{"src":"https:\/\/static001.infoq.cn\/resource\/image\/f2\/03\/f28419eb87cf0cc9a9e7f50439de0a03.gif","alt":null,"title":"","style":[{"key":"width","value":"75%"},{"key":"bordertype","value":"none"}],"href":"","fromPaste":false,"pastePass":false}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":"center","origin":null},"content":[{"type":"text","text":"上图展示了一个跟踪手部运动的软件"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"针对这两个演示，你只需要一个网络摄像头，并且没有数据“离开”你的机器。"}]},{"type":"heading","attrs":{"align":null,"level":3},"content":[{"type":"text","text":"训练你自己的模型，无需任何编码"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"你可以使用 Teachable Machine 训练自己的模型 (不需要编码)。这是一种快速、有趣、简单的在浏览器中创建机器学习模型的方法。例如，你可以教模型识别图像，或者你用麦克风录制的声音。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"image","attrs":{"src":"https:\/\/static001.infoq.cn\/resource\/image\/ca\/d1\/ca13d376a75dde83304146433a82d7d1.png","alt":null,"title":"","style":[{"key":"width","value":"75%"},{"key":"bordertype","value":"none"}],"href":"","fromPaste":false,"pastePass":false}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"三个项目的屏幕截图，你可以使用 Teachable Machine 做：图像项目、音频项目，或姿态项目。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"heading","attrs":{"align":null,"level":3},"content":[{"type":"text","text":"通过教程深入了解"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"TensorFlow 包含一个强大的 Python 库。为了入门学习，在此为初学者和专家提供了一些 教程。这些教程 (包含完整的端到端代码) 涵盖了从机器学习基础到计算机视觉和机器翻译的主题，甚至还展示了如何使用机器学习生成美术作品。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"将 TensorFlow 引入移动应用程序"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"TensorFlow Lite 允许你在移动设备和小型嵌入式设备上构建基于机器学习的应用程序。印度的一群工科生使用 TensorFlow Lite 开发了一款安卓应用程序，通过智能手机摄像头它就能提供当地的空气质量信息。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"image","attrs":{"src":"https:\/\/static001.infoq.cn\/resource\/image\/ac\/45\/ac9e9fdb35f4c71f3ec509d20e3cac45.png","alt":null,"title":"","style":[{"key":"width","value":"75%"},{"key":"bordertype","value":"none"}],"href":"","fromPaste":false,"pastePass":false}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"你还可以做得更小：TensorFlow Lite Micro 可以让你在微控制器上运行机器学习模型 (可以放在你掌上的微型计算机)。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"heading","attrs":{"align":null,"level":3},"content":[{"type":"text","text":"了解如何负责任地建设"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"随着全球数十亿人不断使用以机器学习为核心的产品和服务，负责任地设计和部署这些系统变得越来越重要。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"TensorFlow 包括一套针对于 负责任的人工智能 的工具和最佳实践，包括一款 “假设”工具，该工具用于测试机器学习模型在假设情况下如何为不同的人工作。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"embedcomp","attrs":{"type":"video","data":{"id":"315493","name":"Getting Started with the What-if Tool _ Introducing the What-If Tool.mp4","poster":""}}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"你还可以做更多的事情。TensorFlow 包括一套完整的工具来驱动机器学习系统的生产，它甚至支持量子计算的最新研究。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"这只是个开始，我们很期待接下来的五年会发生什么。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"想了解更多 TensorFlow 的相关信息，请访问 tensorflow.org。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"原文链接："}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"https:\/\/blog.google\/technology\/ai\/5-ways-celebrate-tensorflows-5th-birthday"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"blockquote","content":[{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"译者简介：冬雨，小小技术宅一枚，从事研发过程改进及质量改进方面的工作，关注编程、软件工程、敏捷、DevOps、云计算等领域，非常乐意将国外新鲜的 IT 资讯和深度技术文章翻译分享给大家，已翻译出版《深入敏捷测试》、《持续交付实战》。"}]}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}}]}