Have a question? Connect with the community at the TensorFlow Forum Visit Forum

TensorFlow.js 是可用 JavaScript 開發機器學習的程式庫

以 JavaScript 開發機器學習模型,並直接在瀏覽器或 Node.js 中使用機器學習。

查看教學課程

教學課程會示範如何使用 TensorFlow.js,內容包含完整的端對端範例。

查看模型

經過預先訓練且立即可用的模型,適用於一般的使用案例。

查看示範

使用 TensorFlow.js 在瀏覽器中執行即時示範與範例。

運作方式

執行現有模型

使用現成的 JavaScript 模型或轉換 Python TensorFlow 模型,以便在瀏覽器作業或利用 Node.js 執行。

重新訓練現有模型

使用你自己的資料,重新訓練現有的機器學習模型。

以 JavaScript 開發機器學習

透過彈性且操作直覺的 API,直接使用 JavaScript 打造及訓練模型。

示範

效能循環類神經網路

欣賞類神經網路的即時鋼琴演奏。

網路攝影機控制器

使用在瀏覽器中訓練過的影像來玩小精靈遊戲。

LipSync by YouTube

透過 Facemesh 在瀏覽器中即時同步對嘴熱門單曲〈Dance Monkey〉。

最新消息與公告

請前往我們的網誌查看其他最新消息,並訂閱我們每月發行的 TensorFlow 電子報,直接從你的收件匣收取最新公告。

May 19, 2021  
Run TensorFlow Lite models on the web directly with TensorFlow.js

Unify your mobile and web ML deployments by reusing optimized TF Lite models and running in the browser via WebAssembly, no JavaScript rewrite required. Our new TF.js task APIs support a variety of models and backends.

May 18, 2021  
Speed-up your sites with web-page prefetching using ML

Improve website user experience by training a custom machine learning model with site navigation data to predict next pages, and use an Angular app to prefetch the content and improve site speed.

May 18, 2021  
Machine learning for next gen web apps with TensorFlow.js (Google I/O)

Get a high level overview of what TensorFlow.js is, how it's currently being used, what's new this year, plans for the future, and how you can get involved with our newly formed special interest and working groups.

Continue
May 17, 2021  
Next-generation pose detection with MoveNet

MoveNet is a human pose detection architecture designed to detect difficult poses and fast body motions. The model can run in the browser with very little latency, opening the door for a new class of applications and interactive experiences.