TensorFlow.js: Machine Learning for the Web and Beyond
Daniel Smilkov, Nikhil Thorat, Yannick Assogba et al. · arXiv (Cornell University) · 2019
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.
Cited by 130 works. doi:10.48550/arxiv.1901.05350 Open-access PDF
Authors
- Daniel Smilkov
- Nikhil Thorat
- Yannick Assogba
- Ann Yuan
- Nick Kreeger
- Kangyi Zhang
- Shanqing Cai
- Eric Nielsen
- David A. W. Soergel
- Stan Bileschi
- Michael A. Terry
- Sandeep Gupta
- Sarah Sirajuddin
- D. Sculley
- Rajat Monga
- Greg S. Corrado
- Fernanda Viégas
- MARTIN P. WATTENBERG
References
- Scikit-learn: Machine Learning in Python
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- TensorFlow: A system for large-scale machine learning
- Automatic differentiation in PyTorch
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Scalable parallel programming with CUDA
- Federated Learning of Deep Networks using Model Averaging
- OpenGL Programming Guide: The Official Guide to Learning OpenGL, Version 1.2
- Bringing the web up to speed with WebAssembly
- GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation