TensorFlow.js is a library for machine learning in JavaScript
Develop ML models in JavaScript, and use ML directly in the browser or in Node.js.
How it works
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.
Demos



News & announcements
See updates to help you with your work, and subscribe to our monthly TensorFlow newsletter to get the latest announcements sent directly to your inbox.

The beta version of TF.js integration with AutoML is launched! Build image classification and object detection models using Cloud AutoML without any coding, and download TF.js compatible versions directly.

We have launched the alpha version of first-class React Native support for TF.js, including WebGL acceleration on supported platforms. Learn how to bring performant ML into your React Native app.

On this episode of TensorFlow Meets, Laurence talks with Yannick Assogba, software engineer on the TensorFlow.js team. Learn about training in the browser, and how TensorFlow.js pre-trained and custom models can help you solve your ML use cases.

In this talk, you will learn about the TensorFlow.js ecosystem: how to bring an existing machine learning model into your JS app, re-train the model using your data, and go beyond the browser to other JS platforms.