We may earn an affiliate commission when you visit our partners.

Browser-based Models with TensorFlow.js

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.

Enroll now

Or subscribe to Coursera Plus

And get unlimited access to Coursera

What's inside

Syllabus

Introduction to TensorFlow.js

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.

Image Classification In the Browser

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!

Converting Models to JSON Format

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.

Transfer Learning with Pre-Trained Models

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.

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Appropriate for absolute beginners, as it builds a strong foundation of JavaScript and machine learning concepts

Assumes learners are already familiar with TensorFlow in Python, which may be a barrier to entry for some

Hands-on approach with practical projects provides valuable experience in applying machine learning in real-world scenarios

Focuses heavily on JavaScript and TensorFlow.js, which may limit its relevance for learners interested in other languages and frameworks

Instructors Laurence Moroney are recognized experts in machine learning and have a strong reputation in the field

Part of the TensorFlow for Data and Deployment Specialization, providing a structured learning path for learners interested in machine learning deployment

Save this course

Save Browser-based Models with TensorFlow.js to your list so you can find it easily later:

Save

Reviews summary

Easy-to-understand tensorflow.js

According to students, this course provides an easy-to-understand path for deepening your understanding of TensorFlow.js. Learners say that assignments are well-structured and provide practical experience in deploying machine learning models in the browser. The course is seen positively, although students do note some audio issues and a heavy reliance on copying code for assignments.

This course focuses on the practical aspects of deploying machine learning models in the browser.

"I have learned many things in this course. Tensorflow.js is really interesting and here they explain very well how to train, convert and test on the browser the models."

"The course was neat and clear in terms of details on Tensorflow JS. A bit more details on what are the practical area where this is used at the moment could have been useful."

"This course is very practical and interesting. I enjoyed the excitement I got along the way."

"The lecture content is clear, the quizz are not very interesting, and the assignments mostly are copy paste of the exercises, so not much challenge there."

The audio in the videos is often too quiet.

"The audio volume of the videos in this course is extremely low (compared to 5 courses I took by Andrew Ng) and make it very hard to listen."

"the course content is very good but the instructions on how to install Tensorflow 2.0 and Tensorflow.js in python 3 are not clear."

Assignments often require copying and pasting code from examples, which limits learning.

"The audio volume of the videos in this course is extremely low (compared to 5 courses I took by Andrew Ng) and make it very hard to listen."

"the course content is very good but the instructions on how to install Tensorflow 2.0 and Tensorflow.js in python 3 are not clear."

"The course is easy to follow up and is very easy to pass the graded exercises as you only need to copy-paste code from examples."

Grading for assignments is confusing and often fails due to version dependency issues.

"A lot of explanation of obvious things. Also, excercises are low quality, with Week 3 and 4 quite hard to pass because of technical issues."

"The grading mechanisms for weekly exercises can be confusing and difficult to understand why a submission failed."

"Laurence Moronay is really a great teacher and the course is very interesting and pleasant."

"3rd and 4th week assignments are quite problematic: 3rd week is heavily dependent on python and libraries versions in user's environment and the course does not point which combination is the one which will be graded correctly."

The course relies on specific versions of libraries, which can cause confusion and difficulty for students.

"The grading mechanisms for weekly exercises can be confusing and difficult to understand why a submission failed."

"The version requirement tensorflow for the Week 3 assignment needs to be emphasis to avoid wasting everyone's valuable time."

"I have removed 2 stars for the time wasted trying to make the examples and exercises provided with the course work :=> Mobilenet Model version not compliant with the grader"

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Browser-based Models with TensorFlow.js with these activities:

Review Linear Algebra and Calculus

Show steps

Refresh your understanding of linear algebra and calculus to enhance your comprehension of machine learning concepts.

Browse courses on Linear Algebra

Show steps

Review concepts such as vectors, matrices, and linear transformations.
Practice solving calculus problems involving derivatives and integrals.

Review JavaScript Fundamentals

Show steps

Strengthen your foundation in JavaScript to enhance your ability to implement machine learning models in the browser.

Browse courses on JavaScript

Show steps

Review key JavaScript concepts such as variables, data types, and functions.
Practice writing simple JavaScript programs.

Gather Resources on TensorFlow.js

Show steps

Consolidate your learning resources by compiling a collection of helpful articles, tutorials, and documentation on TensorFlow.js.

Browse courses on TensorFlow.js

Show steps

Search online for tutorials, articles, and documentation on TensorFlow.js.
Organize the resources into a structured folder or document.

Five other activities

Expand to see all activities and additional details

Show all eight activities

Walkthrough TensorFlow.js Tutorials

Show steps

Build a foundation in TensorFlow.js by following official tutorials to get hands-on experience.

Browse courses on TensorFlow.js

Show steps

Go through the TensorFlow.js tutorials on the official website.
Create a simple image classification model.

Join Online TensorFlow.js Study Group

Show steps

Connect with other students and discuss course concepts, share knowledge, and work through challenges together.

Browse courses on TensorFlow.js

Show steps

Find or create an online study group focused on TensorFlow.js.
Participate in group discussions and collaborate on projects.

Build Image Classification Projects

Show steps

Reinforce your understanding by creating image classification projects and experimenting with different model architectures and parameters.

Browse courses on TensorFlow.js

Show steps

Develop a project to classify handwritten digits using TensorFlow.js.
Create a project to recognize objects in webcam feed.

Build a Transfer Learning Model

Show steps

Deepen your understanding of transfer learning by applying it to a real-world problem, such as building a model to recognize gestures.

Browse courses on TensorFlow.js

Show steps

Choose a pre-trained model and dataset for your chosen task.
Convert the model to JSON format.
Train the model on your dataset.
Evaluate the model's performance and make adjustments as needed.

Contribute to Open Source TensorFlow.js Projects

Show steps

Contribute directly to the TensorFlow.js community by reporting bugs, suggesting features, or developing code improvements.

Browse courses on TensorFlow.js

Show steps

Identify areas where you can contribute to open source TensorFlow.js projects.
Submit bug reports or feature requests on GitHub.
Contribute code changes and collaborate on pull requests.

Career center

Learners who complete Browser-based Models with TensorFlow.js will develop knowledge and skills that may be useful to these careers:

Frontend Developer

Frontend developers who work with TensorFlow.js can create interactive and engaging web applications that leverage machine learning capabilities. This course provides a solid foundation in TensorFlow.js, enabling you to build robust and performant frontends that seamlessly integrate machine learning models. By mastering the techniques taught in this course, you'll be well-equipped to develop cutting-edge web applications that harness the power of machine learning.

See salaries and explore the career path for Frontend Developer

Backend Developer

For backend developers, TensorFlow.js offers a unique opportunity to bring machine learning models to the server-side. This course empowers you to build Node.js applications that seamlessly integrate machine learning models, enabling you to process and analyze data in real-time, make predictions, and provide intelligent responses. With the skills gained from this course, you'll be able to enhance the capabilities of your backend systems and develop innovative solutions that leverage machine learning.

See salaries and explore the career path for Backend Developer

Data Scientist

Data scientists who are proficient in TensorFlow.js can develop and deploy machine learning models directly in web browsers. This course covers the fundamentals of TensorFlow.js, providing you with the skills to create interactive data visualizations, perform real-time data analysis, and build predictive models that run entirely within the browser. By completing this course, you'll expand your skillset and become a more versatile data scientist capable of delivering end-to-end machine learning solutions.

See salaries and explore the career path for Data Scientist

Machine Learning Engineer

Machine learning engineers who are familiar with TensorFlow.js can extend their capabilities to the browser environment. This course delves into the intricacies of deploying and running machine learning models in web browsers. You'll learn how to optimize models for performance, handle data efficiently, and integrate machine learning into existing web applications. With the knowledge gained from this course, you'll be able to develop innovative machine learning solutions that run seamlessly in the browser, opening up new possibilities for user engagement and data analysis.

See salaries and explore the career path for Machine Learning Engineer

Web Developer

Web developers can leverage TensorFlow.js to create dynamic and intelligent web applications. This course provides a comprehensive introduction to TensorFlow.js, enabling you to build interactive web pages that incorporate machine learning capabilities. You'll learn how to train models, perform inference, and integrate machine learning into your web development workflow. By mastering the techniques taught in this course, you'll become a well-rounded web developer capable of creating next-generation web applications that leverage the power of machine learning.

See salaries and explore the career path for Web Developer

Software Engineer

Software engineers who are proficient in TensorFlow.js can develop robust and scalable software solutions that incorporate machine learning capabilities. This course introduces the fundamentals of TensorFlow.js, providing you with the skills to build machine learning models that run efficiently within software applications. You'll learn how to integrate machine learning into your software development process, enabling you to create intelligent and data-driven applications.

See salaries and explore the career path for Software Engineer

Data Analyst

Data analysts who are familiar with TensorFlow.js can gain valuable skills for building interactive data visualizations and dashboards. This course provides a practical introduction to TensorFlow.js, enabling you to create data-driven web applications that allow users to explore and analyze data in real-time. You'll learn how to use machine learning techniques to uncover insights from data and present them in visually appealing and interactive formats.

See salaries and explore the career path for Data Analyst

Product Manager

Product managers who have a basic understanding of TensorFlow.js can make informed decisions about incorporating machine learning into their products. This course provides an overview of the capabilities and limitations of TensorFlow.js, enabling you to evaluate its potential for enhancing your products. You'll learn how to identify use cases where TensorFlow.js can add value, and how to communicate the benefits of machine learning to stakeholders.

See salaries and explore the career path for Product Manager

Business Analyst

Business analysts who are familiar with TensorFlow.js can gain valuable insights into the potential of machine learning for business applications. This course provides a non-technical introduction to TensorFlow.js, enabling you to understand how machine learning can be used to solve business problems. You'll learn about different types of machine learning models, their applications in various industries, and how to evaluate their impact on business outcomes.

See salaries and explore the career path for Business Analyst

Marketing Analyst

Marketing analysts who have a basic understanding of TensorFlow.js can gain insights into using machine learning for marketing campaigns. This course provides a practical introduction to TensorFlow.js, enabling you to create data-driven marketing strategies. You'll learn how to use machine learning techniques to analyze customer behavior, segment audiences, and optimize marketing campaigns.

See salaries and explore the career path for Marketing Analyst

UX Designer

UX designers who are familiar with TensorFlow.js can create user experiences that are personalized and data-driven. This course provides an overview of the capabilities of TensorFlow.js, enabling you to understand how machine learning can be used to enhance user interactions. You'll learn about different machine learning techniques that can be applied to UX design, and how to evaluate their impact on user experience.

See salaries and explore the career path for UX Designer

Technical Writer

Technical writers who are proficient in TensorFlow.js can create clear and concise documentation for machine learning applications. This course provides a comprehensive overview of TensorFlow.js, enabling you to understand the technical concepts and principles behind machine learning. You'll learn how to write technical documentation that effectively communicates the capabilities and limitations of TensorFlow.js, making it accessible to a wider audience.

See salaries and explore the career path for Technical Writer

Recruiter

Recruiters who are familiar with TensorFlow.js can identify and attract candidates with in-demand machine learning skills. This course provides an introduction to TensorFlow.js, enabling you to understand the basics of machine learning and its applications. You'll learn about the different roles and responsibilities of machine learning professionals, and how to evaluate candidates' skills and experience.

See salaries and explore the career path for Recruiter

Project Manager

Project managers who have a basic understanding of TensorFlow.js can effectively manage machine learning projects. This course provides an overview of the machine learning project lifecycle, enabling you to understand the key phases and challenges involved. You'll learn about different machine learning methodologies, project planning techniques, and how to manage teams of machine learning engineers.

See salaries and explore the career path for Project Manager

Sales Representative

Sales representatives who are familiar with TensorFlow.js can effectively communicate the value of machine learning solutions to potential customers. This course provides an introduction to TensorFlow.js, enabling you to understand the basics of machine learning and its applications. You'll learn about the different industries and use cases where TensorFlow.js can be applied, and how to demonstrate its benefits to customers.

See salaries and explore the career path for Sales Representative

Reading list

We've selected 12 books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in Browser-based Models with TensorFlow.js.

Deep Learning with Python, Second Edition

Save

A renowned textbook and reference for deep learning, covering fundamental concepts, architectures, and applications, with a focus on Python and Keras.

Browser-based Models with TensorFlow.js

What's inside

Syllabus

Good to know

Save this course

Reviews summary

Easy-to-understand tensorflow.js

Activities

Career center

Reading list

Share

Similar courses