Explore

Browser-based Models with TensorFlow.js

Approx. 17 hours to complete

Save Course

Go to Course

Course Summary

Learn how to build browser-based models using TensorFlow, a powerful machine learning framework. This course covers the fundamentals of TensorFlow and how to use it to build machine learning models that can run in a web browser.

Key Learning Points

Build and train machine learning models using TensorFlow
Deploy models to run in a web browser
Learn how to use TensorFlow.js to build interactive web applications

Learning Outcomes

Ability to build and train machine learning models using TensorFlow
Knowledge of how to deploy models to run in a web browser
Understanding of how to use TensorFlow.js to build interactive web applications

Prerequisites or good to have knowledge before taking this course

Basic knowledge of machine learning concepts
Familiarity with JavaScript

Course Difficulty Level

Intermediate

Course Format

Online
Self-paced
Video lectures
Hands-on exercises

Similar Courses

Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning
Applied Data Science with Python

Related Education Paths

Notable People in This Field

Andrew Ng
François Chollet

Related Books

Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow

Description

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.

Knowledge

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

Outline

Introduction to TensorFlow.js
Specialization Introduction, A Conversation with Andrew Ng
Course Introduction, A Conversation with Andrew Ng
A Few Words From Laurence
Building the Model
Training the Model
First Example In Code
The Iris Dataset
Reading the Data
One-hot Encoding
Designing the NN
Iris Classifier In Code
Getting Your System Ready
Downloading the Ungraded Labs and Programming Assignments
Your First Model
Iris Dataset Documentation
Using the Web Server
Iris Classifier
Week 1 Wrap up

Image Classification In the Browser
Introduction, A Conversation with Andrew Ng
Creating a Convolutional Net with JavaScript
Visualizing the Training Process
What Is a Sprite Sheet?
Using the Sprite Sheet
Using tf.tidy() to Save Memory
A Few Words From Laurence
MNIST Classifier In Code
tfjs-vis Documentation
MNIST Sprite Sheet
MNIST Classifier
Week 2 Wrap up
Exercise Description

Converting Models to JSON Format
Introduction, A Conversation with Andrew Ng
A Few Words From Laurence
Pre-trained TensorFlow.js Models
Toxicity Classifier
Toxicity Classifier In Code
MobileNet
Using MobileNet
Training Results
MobileNet Example In Code
Converting Models to JavaScript
Converting Models to JavaScript In Code
Linear Example In Code
Important Links
Toxicity Classifier
Classes Supported by MobileNet
Image Classification Using MobileNet
Linear Model
Week 3 Wrap up

Transfer Learning with Pre-Trained Models
Introduction, A Conversation with Andrew Ng
A Few Words From Laurence
Building a Simple Web Page
Retraining the MobileNet Model
The Training Function
Capturing the Data
The Dataset Class
Training the Network with the Captured Data
Performing Inference
Rock Paper Scissors In Code
A Conversation with Andrew Ng
Rock Paper Scissors
Exercise Description
Wrap up

Summary of User Reviews

The Browser-based Models with TensorFlow course from Coursera has received positive reviews from students. They have praised the course for its comprehensive and easy-to-follow lessons, as well as its practical approach to learning machine learning. Overall, the course has been highly recommended by many of its users.

Key Aspect Users Liked About This Course

The course's practical approach to learning machine learning.

Pros from User Reviews

Comprehensive and easy-to-follow lessons
Practical approach to learning machine learning
Great for beginners and those with some experience
Interactive and engaging content
Instructors are knowledgeable and helpful

Cons from User Reviews

Some students found the course to be too basic
Limited focus on advanced topics
No opportunity for hands-on experience with TensorFlow
Course materials could be more organized
Some technical issues with the platform

Recommended for you

The Web Developer Bootcamp 2021

COMPLETELY REDONE - The only course you need to learn web development - HTML, CSS, JS, Node, and More! COMPLETELY REDONE WITH OVER 500 BRAND NEW VIDEOS!...

Save Course

Dive Into Ansible - From Beginner to Expert in Ansible

Dive Into Ansible, Learn Ansible/DevOps/Automation, *Latest Ansible Version (4. x) + Full Ansible Lab Included!* It aims to help you master Ansible while tackling and learning multiple topics....

Save Course

Ultimate PHP, Laravel, CSS & Sass! Learn PHP, Laravel & Sass

Learn PHP,Laravel,PDO,Security and create layouts using CSS GRID, Bootstrap, Flexbox,topped up with JavaScript and Ajax This course now is updated with Laravel!...

Save Course