TensorFlow.js: Machine Learning for the Web and Beyond

Abstract

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.

10 pages, expanded performance section, fixed page breaks in code listings

References in corpus (5)

• Scikit-learn: Machine Learning in Python
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation
• Direct-Manipulation Visualization of Deep Networks

Cited by in corpus (16)

• The VIA Annotation Software for Images, Audio and Video
• CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization
• The Bach Doodle: Approachable music composition with machine learning at scale
• WearMask: Fast In-browser Face Mask Detection with Serverless Edge Computing for COVID-19
• Sensible Agent: A Framework for Unobtrusive Interaction with Proactive AR Agents
• Speed Benchmarking of Genetic Programming Frameworks
• JSDoop and TensorFlow.js: Volunteer Distributed Web Browser-Based Neural Network Training
• SurfBraid: A concept tool for preparing and resource estimating quantum circuits protected by the surface code
• exploRNN: Understanding Recurrent Neural Networks through Visual Exploration
• WebSHAP: Towards Explaining Any Machine Learning Models Anywhere
• An Evolution of CNN Object Classifiers on Low-Resolution Images
• Level generation and style enhancement -- deep learning for game development overview
• Nail Polish Try-On: Realtime Semantic Segmentation of Small Objects for Native and Browser Smartphone AR Applications
• Explainability via Interactivity? Supporting Nonexperts' Sensemaking of Pretrained CNN by Interacting with Their Daily Surroundings
• InFL-UX: A Toolkit for Web-Based Interactive Federated Learning
• $C^{3}DRec$: Cloud-Client Cooperative Deep Learning for Temporal Recommendation in the Post-GDPR Era