TensorFlow.js: Machine Learning for the Web and Beyond
It provides a tool for web developers to integrate machine learning directly into web applications, though it is incremental as an extension of the existing TensorFlow ecosystem.
The paper introduces TensorFlow.js, a library enabling machine learning in JavaScript for web browsers and Node.js, allowing models to be ported from Python and empowering JavaScript developers to build and deploy on-device ML applications.
TensorFlow.js is a library for building and executing machine learning algorithms in JavaScript. TensorFlow.js models run in a web browser and in the Node.js environment. The library is part of the TensorFlow ecosystem, providing a set of APIs that are compatible with those in Python, allowing models to be ported between the Python and JavaScript ecosystems. TensorFlow.js has empowered a new set of developers from the extensive JavaScript community to build and deploy machine learning models and enabled new classes of on-device computation. This paper describes the design, API, and implementation of TensorFlow.js, and highlights some of the impactful use cases.