TensorFlow.js | TensorFlow

TensorFlow.js is a library for developing and training ML models in JavaScript, and deploying in browser or on Node.js

Tutorials show you how to use TensorFlow.js with complete, end-to-end examples.

Guides explain the concepts and components of TensorFlow.js.

Live demos and examples run in your browser using TensorFlow.js.

Run existing models

Use off-the-shelf JavaScript models or convert Python TensorFlow models to run in the browser or under Node.js.

Retrain existing models

Retrain pre-existing ML models using your own data.

Develop ML with JavaScript

Build and train models directly in JavaScript using flexible and intuitive APIs.

Emoji Scavenger Hunt

Use your phone’s camera to identify emojis in the real world. Can you find all the emojis before time expires?

Webcam Controller

Play Pac-Man using images trained in your browser.

Move Mirror

Explore pictures in a fun new way, just by moving around.

May 9, 2018

TensorFlow for JavaScript (Google I/O '18)

This session will offer a detailed description of how to use JavaScript to train and deploy your models.

Oct 10, 2018

A look at how we built the Emoji Scavenger Hunt using TensorFlow.js

Explore how Google Brand Studio trained a custom model for object recognition and used it on the web front-end with TensorFlow.js.

Jul 19, 2018

Move Mirror: An AI Experiment with Pose Estimation in the Browser using TensorFlow.js

How TensorFlow.js supported the launch of the experiment Move Mirror, and make pose estimation more widely accessible.

Jun 10, 2018

Abstract Art with ML

Learn how randomly initialized neural networks are able to produce visually appealing images.

Gallery of community built TensorFlow.js projects

TensorFlow.js on GitHub

Ask a question on StackOverflow

Issues, bug reports, and feature requests

Community discussion forum

Announcement-only mailing list