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
Watch the Dev Summit presentation to see all that is new for TensorFlow.js and learn about upcoming features, improvements and releases.
See how L'Oréal's Modiface team uses TensorFlow.js to make makeup try on as easy as visiting a website.
Learn about the new platform integration and capabilities such as GPU accelerated backend, model loading and saving, training custom models, and image and video handling.
Use a Python model in Node.js without having to convert it. You may even see a performance boost too.
