Coding With Fun
Home Docker Django Node.js Articles Python pip guide FAQ Policy

What's the difference between tensorflow and tensorflow.js?


Asked by Dominik Giles on Dec 13, 2021 FAQ



TensorFlow and TensorFlow.js can be categorized as "Machine Learning" tools. TensorFlow.js is an open source tool with 11.2K GitHub stars and 816 GitHub forks. Here's a link to TensorFlow.js's open source repository on GitHub.
And,
TensorFlow can be used for both network training and inference, whereas TensorFlow Lite is specifically designed for inference on devices with limited compute (phones, tablets and other embedded devices).
In addition, Tensorflow works on a static graph concept that means the user first has to define the computation graph of the model and then run the ML model, whereas PyTorch believes in a dynamic graph that allows defining/manipulating the graph on the go. PyTorch offers an advantage with its dynamic nature of creating graphs.
Moreover,
The lower-level Tensorflow functions tend to be used for huge models that need to run quickly, while the higher-level Keras functions tend to be used for everything else. If you really want to see how the lower-level API works in action, I have a few code snippets that exhibit some of Tensorflow’s features.
Keeping this in consideration,
In March 2018, Google announced TensorFlow.js version 1.0 for machine learning in JavaScript. In Jan 2019, Google announced TensorFlow 2.0. It became officially available in Sep 2019. In May 2019, Google announced TensorFlow Graphics for deep learning in computer graphics.