TensorFlow.js is a JavaScript Library for training and deploying machine learning models in the browser and in Node.js.
See the sections below for different ways you can get started.
Code ML programs without dealing directly with Tensors
Want to get started with Machine Learning but not worry about any low level details like Tensors or Optimizers?
Built on top of TensorFlow.js, the ml5.js library provides access to machine learning algorithms and models in the browser with a concise, approachable API.
Get Setup with TensorFlow.js
Comfortable with concepts like Tensors, Layers, Optimizers and Loss Functions (or willing to get comfortable with them)? TensorFlow.js provides flexible building blocks for neural network programming in JavaScript.
See how to get up and running with TensorFlow.js code in the browser or Node.js.
Convert Pretrained Models to TensorFlow.js
Learn how to convert pretrained models from Python into TensorFlow.js
Learn from existing TensorFlow.js code
tfjs-examples provides small code examples that implement various ML tasks using TensorFlow.js.
Visualize the Behaviour of your TensorFlow.js Model
tfjs-vis is a small library for in browser visualization intended for use with TensorFlow.js.
Get your data ready for processing with TensorFlow.js
TensorFlow.js has support for processing data using ML best practices.