Download
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. Use off-the-shelf JavaScript models or convert Python TensorFlow models to run in the browser or under Node.js. Retrain pre-existing ML models using your own data. Build and train models directly in JavaScript using flexible and intuitive APIs. Tensors are the core datastructure of TensorFlow.js They are a generalization of vectors and matrices to potentially higher dimensions. 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. 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.
Features
- JavaScript Library for training and deploying machine learning models in the browser
- Code ML programs without dealing directly with Tensors
- TensorFlow.js provides flexible building blocks for neural network programming in JavaScript
- Convert Pretrained Models to TensorFlow.js
- Retrain pre-existing ML models using your own data
- Includes TensorFlow.js Vis, an in-browser visualization for TensorFlow.js models
Project Samples
