Getting Started with Tensorflow.js

Offered By
Coursera Project Network
In this Guided Project, you will:

Set up a browser-based project using script tags and an HTML body

Import pre-trained Keras models into a Tensorflow.js web app

Code a prototype Web app using Tensorflow.js

Clock2 hours
IntermediateIntermediate
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

By the end of this project, you will learn how to code a smart webcam to detect people and other everyday objects using a pre-trained COCO-SSD image recognition model with Tensorflow.js. Based on an older library called deeplearn.js, Tensorflow.js is a deep learning library that leverages Tensorflow to create, train and run inference on artificial neural network models directly in a web browser, utilizing the client's GPU/CPU resources (accelerated using WebGL). Tensorflow.js brings Tensorflow to the web! JavaScript/Typescript experience is heavily recommended. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Skills you will develop

Deep LearningHtmlWeb ApplicationTensorflowJavaScript

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Getting Familiar with Tensorflow.js

  2. Using ml5js

  3. Setting up a Tensorflow.js Project

  4. We are going to very briefly cover CSS styling in the p5js editor

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.