Browser-based Models with TensorFlow.js

Browser-based Models with TensorFlow.js

This course is part of TensorFlow: Data and Deployment Specialization

Instructor: Laurence Moroney

Access provided by University of Nevada, Reno

50,167 already enrolled

4 modules

Gain insight into a topic and learn the fundamentals.

1,011 reviews

Intermediate level

Recommended experience

Flexible schedule

2 weeks at 10 hours a week

Learn at your own pace

95%

Most learners liked this course

4 modules

Gain insight into a topic and learn the fundamentals.

1,011 reviews

Intermediate level

Recommended experience

Flexible schedule

2 weeks at 10 hours a week

Learn at your own pace

95%

Most learners liked this course

What you'll learn

Train and run inference in a browser
Handle data in a browser
Build an object classification and recognition model using a webcam

Skills you'll gain

Tools you'll learn

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

5 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your subject-matter expertise

This course is part of the TensorFlow: Data and Deployment Specialization

When you enroll in this course, you'll also be enrolled in this Specialization.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate

There are 4 modules in this course

Bringing a machine learning model into the real world involves a lot more than just modeling. This Specialization will teach you how to navigate various deployment scenarios and use data more effectively to train your model.

In this first course, you’ll train and run machine learning models in any browser using TensorFlow.js. You’ll learn techniques for handling data in the browser, and at the end you’ll build a computer vision project that recognizes and classifies objects from a webcam. This Specialization builds upon our TensorFlow in Practice Specialization. If you are new to TensorFlow, we recommend that you take the TensorFlow in Practice Specialization first. To develop a deeper, foundational understanding of how neural networks work, we recommend that you take the Deep Learning Specialization.

Welcome to Browser-based Models with TensorFlow.js, the first course of the TensorFlow for Data and Deployment Specialization. In this first course, we’re going to look at how to train machine learning models in the browser and how to use them to perform inference using JavaScript. This will allow you to use machine learning directly in the browser as well as on backend servers like Node.js. In the first week of the course, we are going to build some basic models using JavaScript and we'll execute them in simple web pages.

What's included

11 videos9 readings2 assignments1 programming assignment1 app item

11 videos Total 30 minutes

Specialization Introduction, A Conversation with Andrew Ng 1 minute
Course Introduction, A Conversation with Andrew Ng 1 minute
A Few Words From Laurence 2 minutes
Building the Model 3 minutes
Training the Model 3 minutes
First Example In Code 4 minutes
The Iris Dataset 1 minute
Reading the Data 4 minutes
One-hot Encoding 1 minute
Designing the NN 2 minutes
Iris Classifier In Code 6 minutes

9 readings Total 73 minutes

Getting Your System Ready 10 minutes
Downloading the Ungraded Labs and Programming Assignments 10 minutes
Join the DeepLearning.AI Forum to ask questions, get support, or share amazing ideas! 2 minutes
Your First Model 10 minutes
Iris Dataset Documentation 10 minutes
Using the Web Server 10 minutes
Iris Classifier 10 minutes
Week 1 Wrap up 10 minutes
Lecture Notes Week 1 1 minute

2 assignments

Quiz 1 0 minutes
One-Hot Encoding 0 minutes

1 programming assignment Total 180 minutes

Week 1 - Breast Cancer Classification 180 minutes

1 app item Total 1 minute

Intake Survey 1 minute

This week we'll look at Computer Vision problems, including some of the unique considerations when using JavaScript, such as handling thousands of images for training. By the end of this module you will know how to build a site that lets you draw in the browser and recognizes your handwritten digits!

What's included

8 videos6 readings1 assignment1 programming assignment

8 videos Total 27 minutes

Introduction, A Conversation with Andrew Ng 1 minute
Creating a Convolutional Net with JavaScript 4 minutes
Visualizing the Training Process 2 minutes
What Is a Sprite Sheet? 1 minute
Using the Sprite Sheet 3 minutes
Using tf.tidy() to Save Memory 1 minute
MNIST Classifier In Code 13 minutes
A Few Words From Laurence 0 minutes

6 readings Total 51 minutes

tfjs-vis Documentation 10 minutes
MNIST Sprite Sheet 10 minutes
MNIST Classifier 10 minutes
Week 2 Wrap up 10 minutes
Lecture Notes Week 2 1 minute
Exercise Description 10 minutes

1 assignment Total 30 minutes

Week 2 Quiz 30 minutes

1 programming assignment Total 180 minutes

Week 2 - Fashion MNIST Classifier 180 minutes

This week we'll see how to take models that have been created with TensorFlow in Python and convert them to JSON format so that they can run in the browser using Javascript. We will start by looking at two models that have already been pre-converted. One of them is going to be a toxicity classifier, which uses NLP to determine if a phrase is toxic in a number of categories; the other one is Mobilenet which can be used to detect content in images. By the end of this module, you will train a model in Python yourself and convert it to JSON format using the tensorflow.js converter.

What's included

12 videos7 readings1 assignment1 programming assignment1 ungraded lab

12 videos Total 28 minutes

Introduction, A Conversation with Andrew Ng 2 minutes
A Few Words From Laurence 1 minute
Pre-trained TensorFlow.js Models 1 minute
Toxicity Classifier 4 minutes
Toxicity Classifier In Code 4 minutes
MobileNet 1 minute
Using MobileNet 2 minutes
Training Results 2 minutes
MobileNet Example In Code 4 minutes
Converting Models to JavaScript 5 minutes
Converting Models to JavaScript In Code 2 minutes
Linear Example In Code 2 minutes

7 readings Total 61 minutes

Important Links 10 minutes
Toxicity Classifier 10 minutes
Classes Supported by MobileNet 10 minutes
Image Classification Using MobileNet 10 minutes
Linear Model 10 minutes
Week 3 Wrap up 10 minutes
Lecture Notes Week 3 1 minute

1 assignment

Week 3 Quiz 0 minutes

1 programming assignment Total 180 minutes

Week 3 - Converting a Python Model to JavaScript 180 minutes

1 ungraded lab Total 60 minutes

Week 3: Converting a Python Model to JavaScript 60 minutes

One final work type that you'll need when creating Machine Learned applications in the browser is to understand how transfer learning works. This week you'll build a complete web site that uses TensorFlow.js, capturing data from the web cam, and re-training mobilenet to recognize Rock, Paper and Scissors gestures.

What's included

11 videos5 readings1 assignment1 programming assignment

11 videos Total 26 minutes

Introduction, A Conversation with Andrew Ng 1 minute
A Few Words From Laurence 1 minute
Building a Simple Web Page 2 minutes
Retraining the MobileNet Model 2 minutes
The Training Function 2 minutes
Capturing the Data 4 minutes
The Dataset Class 2 minutes
Training the Network with the Captured Data 2 minutes
Performing Inference 5 minutes
Rock Paper Scissors In Code 4 minutes
A Conversation with Andrew Ng 1 minute

5 readings Total 33 minutes

Rock Paper Scissors 10 minutes
Lecture Notes Week 4 1 minute
[IMPORTANT] Reminder about end of access to Lab Notebooks 2 minutes
Exercise Description 10 minutes
Wrap up 10 minutes

1 assignment

Week 4 Quiz 0 minutes

1 programming assignment Total 180 minutes

Week 4 - Rock Paper Scissors 180 minutes

Earn a career certificate

Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.

Instructor

Instructor ratings

(181 ratings)

Laurence Moroney

DeepLearning.AI

22 Courses 595,404 learners

Offered by

DeepLearning.AI

Why people choose Coursera for their career

Felipe M.

Learner since 2018

"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."

Jennifer J.

Learner since 2020

"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."

Larry W.

Learner since 2021

"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."

Chaitanya A.

"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

Learner reviews

5 stars
82.31%
4 stars
13.63%
3 stars
2.56%
2 stars
0.69%
1 star
0.79%

Showing 3 of 1011

Reviewed on May 3, 2021

This course has given me a lot of real world exercises. The lessons are concise yet really helpful to start your web-based AI project.

Reviewed on Mar 2, 2020

I really enjoy working on the programming assignments of this course especially the Week 4 one which is fun and have a lot to learn!

Reviewed on Jul 3, 2020

Excellent presentation of material and lab examples.Final assignment is really inspiring and motivating. Thank you for putting effort to design such content.

View more reviews