TensorFlow五週年，官方發佈“慶祝指南”

{"type":"doc","content":[{"type":"blockquote","content":[{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"2015年，谷歌開源了用於研究和生產的機器學習框架——TensorFlow，如今它已經走過了五年，並且成爲最流行的機器學習框架之一。在 TensorFlow 五週年之際，谷歌官網發佈了一篇文章來爲它慶生。"}]}]},{"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，我們開源了 TensorFlow，這是我們用於研究和生產的一款機器學習框架。我們的目標是讓任何人都可以用到最先進的機器學習工具。"}]},{"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":"從那時起，TensorFlow 已經成爲世界上最受歡迎的機器學習庫，下載量超過 1.6 億次。看到這麼多人使用 TensorFlow 讓我們感到有些難以置信、羞愧難當。感謝世界各地數以千計的非谷歌人士，他們貢獻過代碼、創建過教育課程、組織過開發活動，爲 TensorFlow 和不斷壯大的機器學習社區提供了大力支持。"}]},{"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":"爲慶祝 TensorFlow 誕生五週年，我們提供了一些交互演示，在瀏覽器中點點鼠標即可進行嘗試，還有一些可以幫助你創建自己的項目的教程。如果你剛剛接觸 TensorFlow，這是瞭解它的功能的一個絕佳方法。如果你喜歡這些內容，想要進一步深入瞭解，請瀏覽 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":"試試由機器學習驅動的交互式演示"}]},{"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 支持多種編程語言和環境。我們先來看一個 JavaScript 的快速展覽，以及三個只需單擊鼠標即可嘗試的交互式演示。"}]},{"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 允許你完全在瀏覽器中編寫和運行機器學習模型。這對於隱私保護應用程序 (不需要將數據發送到服務器) 和交互式機器學習程序都有重要的意義。"}]},{"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 的地標跟蹤程序 是一個很好的例子，它支持免手動接口和輔助技術；你可以在你的瀏覽器中自己嘗試這個模型 (耐心等待一會兒，可能需要一些時間加載！)"}]},{"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":"動畫演示軟件通過分析虹膜來進行跟蹤"}]},{"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":"與眼球跟蹤類似，你也可以使用 TensorFlow.js 來跟蹤 手部運動。"}]},{"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":"上圖展示了一個跟蹤手部運動的軟件"}]},{"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":"針對這兩個演示，你只需要一個網絡攝像頭，並且沒有數據“離開”你的機器。"}]},{"type":"heading","attrs":{"align":null,"level":3},"content":[{"type":"text","text":"訓練你自己的模型，無需任何編碼"}]},{"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 訓練自己的模型 (不需要編碼)。這是一種快速、有趣、簡單的在瀏覽器中創建機器學習模型的方法。例如，你可以教模型識別圖像，或者你用麥克風錄製的聲音。"}]},{"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":"三個項目的屏幕截圖，你可以使用 Teachable Machine 做：圖像項目、音頻項目，或姿態項目。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"heading","attrs":{"align":null,"level":3},"content":[{"type":"text","text":"通過教程深入瞭解"}]},{"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 包含一個強大的 Python 庫。爲了入門學習，在此爲初學者和專家提供了一些 教程。這些教程 (包含完整的端到端代碼) 涵蓋了從機器學習基礎到計算機視覺和機器翻譯的主題，甚至還展示瞭如何使用機器學習生成美術作品。"}]},{"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":"將 TensorFlow 引入移動應用程序"}]},{"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 允許你在移動設備和小型嵌入式設備上構建基於機器學習的應用程序。印度的一羣工科生使用 TensorFlow Lite 開發了一款安卓應用程序，通過智能手機攝像頭它就能提供當地的空氣質量信息。"}]},{"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":"你還可以做得更小：TensorFlow Lite Micro 可以讓你在微控制器上運行機器學習模型 (可以放在你掌上的微型計算機)。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"heading","attrs":{"align":null,"level":3},"content":[{"type":"text","text":"瞭解如何負責任地建設"}]},{"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":"隨着全球數十億人不斷使用以機器學習爲核心的產品和服務，負責任地設計和部署這些系統變得越來越重要。"}]},{"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 包括一套針對於 負責任的人工智能 的工具和最佳實踐，包括一款 “假設”工具，該工具用於測試機器學習模型在假設情況下如何爲不同的人工作。"}]},{"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":"你還可以做更多的事情。TensorFlow 包括一套完整的工具來驅動機器學習系統的生產，它甚至支持量子計算的最新研究。"}]},{"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":"這只是個開始，我們很期待接下來的五年會發生什麼。"}]},{"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 的相關信息，請訪問 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":"原文鏈接："}]},{"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":"譯者簡介：冬雨，小小技術宅一枚，從事研發過程改進及質量改進方面的工作，關注編程、軟件工程、敏捷、DevOps、雲計算等領域，非常樂意將國外新鮮的 IT 資訊和深度技術文章翻譯分享給大家，已翻譯出版《深入敏捷測試》、《持續交付實戰》。"}]}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}}]}