From the course: Learning TensorFlow with JavaScript
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Differences between versions
From the course: Learning TensorFlow with JavaScript
Differences between versions
- [Instructor] If you ever used Deeplearn.js, TensorFlow.js has basically evolved from this library with the addition of several tools to import TensorFlow in Keras models and has now replaced it. What are the major differences in between the regular TensorFlow and the Java Script version? One, is performance. The regular version runs 1.5 faster than the Java Script version, and that is mostly due to how it is used at its core. TensorFlow.js runs in the browser, therefore, a lot CPU processes are used for your browsing experience, plus running it on WebGL versus Python with AVX. If you've ever used TensorFlow, the non-js version, in the past, you'll notice a performance decrease. Also with a recent wrapper, you can run TensorFlow.js in Node.js, so not in the browser, if you choose to do so. But in most cases, you really want to use the js version if you want to do Machine Learning in the browser. And for any other use where you want to play with data in the server environment, you'd…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.