Attend the Women in ML Symposium on December 7 Register now

Get started

Stay organized with collections Save and categorize content based on your preferences.

TensorFlow.js is a JavaScript library for training and deploying machine learning models in the web browser and in Node.js.

This page lists some ways to get started with TensorFlow.js.

Code ML programs without dealing directly with tensors

If you want to get started with machine learning without managing optimizers or tensor manipulation, then check out the ml5.js library.

Built on top of TensorFlow.js, the ml5.js library provides access to machine learning algorithms and models in the web browser with a concise, approachable API.

Check Out ml5.js

Install TensorFlow.js

See how to install TensorFlow.js for implementation in the web browser or Node.js.

Install TensorFlow.js

Convert pretrained models to TensorFlow.js

Learn how to convert pretrained models from Python to TensorFlow.js.

Keras Model GraphDef Model

Learn from existing TensorFlow.js code

The tfjs-examples repository provides small example implementations for various ML tasks using TensorFlow.js.

View tfjs-examples on GitHub

Visualize the behavior of your TensorFlow.js model

tfjs-vis is a small library for visualization in the web browser intended for use with TensorFlow.js.

View tfjs-vis on GitHub See Demo

Prepare data for processing with TensorFlow.js

TensorFlow.js has support for processing data using ML best practices.

View Documentation