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.
This course is part of the TensorFlow: Data and Deployment Specialization
Browser-based Models with TensorFlow.js
Offered By
About this Course
75,076 recent views
What you will 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 will gain
Convolutional Neural NetworkMachine LearningTensorflowObject DetectionTensorFlow.js
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Course 1 of 4 in the
Flexible deadlines
Reset deadlines in accordance to your schedule.
Intermediate Level
Basic understanding of JavaScript
Approx. 13 hours to complete
Suggested: 4 weeks of study, 4-5 hours/week
English
Subtitles: English
Syllabus - What you will learn from this course
5 hours to complete
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.
5 hours to complete
11 videos (Total 30 min), 7 readings, 3 quizzes
11 videos
Course Introduction, A Conversation with Andrew Ng1m
A Few Words From Laurence2m
Building the Model3m
Training the Model3m
First Example In Code4m
The Iris Dataset1m
Reading the Data4m
One-hot Encoding1m
Designing the NN2m
Iris Classifier In Code6m
7 readings
Getting Your System Ready10m
Downloading the Coding Examples and Exercises10m
Your First Model10m
Iris Dataset Documentation10m
Using the Web Server10m
Iris Classifier10m
Week 1 Wrap up10m
2 practice exercises
Quiz 1
One-Hot Encoding
4 hours to complete
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!
4 hours to complete
8 videos (Total 27 min), 5 readings, 2 quizzes
8 videos
Creating a Convolutional Net with JavaScript4m
Visualizing the Training Process2m
What Is a Sprite Sheet?1m
Using the Sprite Sheet2m
Using tf.tidy() to Save Memory1m
A Few Words From Laurence24s
MNIST Classifier In Code13m
5 readings
tjs-vis Documentation10m
MNIST Sprite Sheet10m
MNIST Classifier10m
Week 2 Wrap up10m
Exercise Description10m
1 practice exercise
Week 2 Quiz
5 hours to complete
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.
5 hours to complete
12 videos (Total 28 min), 7 readings, 2 quizzes
12 videos
A Few Words From Laurence1m
Pre-trained TensorFlow.js Models49s
Toxicity Classifier3m
Toxicity Classifier In Code3m
MobileNet49s
Using MobileNet1m
Training Results1m
MobileNet Example In Code3m
Converting Models to JavaScript4m
Converting Models to JavaScript In Code2m
Linear Example In Code1m
7 readings
Important Links10m
Toxicity Classifier10m
Classes Supported by MobileNet10m
Image Classification Using MobileNet10m
Linear Model10m
Week 3 Wrap up10m
Optional - Install Wget (Only If Needed)10m
1 practice exercise
Week 3 Quiz
4 hours to complete
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.
4 hours to complete
11 videos (Total 26 min), 3 readings, 2 quizzes
11 videos
A Few Words From Laurence53s
Building a Simple Web Page2m
Retraining the MobileNet Model1m
The Training Function2m
Capturing the Data3m
The Dataset Class2m
Training the Network with the Captured Data1m
Performing Inference4m
Rock Paper Scissors In Code4m
A Conversation with Andrew Ng1m
3 readings
Rock Paper Scissors10m
Exercise Description10m
Wrap up10m
1 practice exercise
Week 4 Quiz
Reviews
4.7
TOP REVIEWS FROM BROWSER-BASED MODELS WITH TENSORFLOW.JS
by ZBDec 19, 2019
Awesome - elegant in its complex simplicity. Clear explanations, logical curriculum structure, nice and knowledgeable code examples. A must-complete course indeed!
by SSJan 1, 2020
Thanks to Laurence and Andrew for designing such a great course. I learnt a lot from this course and looking forward to learn more from both of you.
by SZFeb 23, 2020
Awesome course! This is one of the most practical courses I have taken, and I am looking forward to the next courses in the series. Thanks! - Steve
by JCMar 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!
by VVDec 17, 2019
Great course! A bit of a learning curve on javascript, but really worth it! The exercise in Week 4 was phenomenal! Thanks.
by PMDec 17, 2019
Last exercise was really difficult to pass! Probably due to overfitting and not generalising to the the test set.
by PGDec 16, 2019
Great videos and nice coding challenges. Would like some more support on various error messages though
by RSFeb 19, 2020
Great resource to build practical, real-world examples...easily explained with lots of sample code.
by ECJan 4, 2020
Excellent! well presented and guided through. A good starting point to begin playing with the tech!
by MBDec 27, 2019
Great introduction on browser-based models. Well presented with great code examples and exercises.
by OHFeb 6, 2020
This was an awesome course with everything well explained and with some really cool projects.
by SBFeb 5, 2020
Good introductory course on Tensorflow deployment. Enjoyed lectures and doing assignments.
by PTMar 7, 2020
Great for a beginner. Projects you can show in interviews can be made using given skills
by SAJan 3, 2020
Great course to begin with for those who wants to upgrade their deployment methods
by HAFeb 27, 2020
Thank you for the great course, I have learned a lot in a short time!
by DJJan 5, 2020
The course is really clear, but I feel that it's lacking in content.
by VSDec 31, 2019
Awesome course with very good content.Thanks Laurence.
by USFeb 26, 2020
Amazing content and a great way of explaining stuff
by GLFeb 22, 2020
Excellent review of TensorFlow.js and useful code!
Offered by
deeplearning.ai
deeplearning.ai is Andrew Ng's new venture which amongst others, strives for providing comprehensive AI education beyond borders.
About the TensorFlow: Data and Deployment Specialization
Continue developing your skills in TensorFlow as you learn to navigate through a wide range of deployment scenarios and discover new ways to use data more effectively when training your machine learning models.
In this four-course Specialization, you’ll learn how to get your machine learning models into the hands of real people on all kinds of devices. Start by understanding how to train and run machine learning models in browsers and in mobile applications. Learn how to leverage built-in datasets with just a few lines of code, learn about data pipelines with TensorFlow data services, use APIs to control data splitting, process all types of unstructured data and retrain deployed models with user data while maintaining data privacy. Apply your knowledge in various deployment scenarios and get introduced to TensorFlow Serving, TensorFlow, Hub, TensorBoard, and more.
Industries all around the world are adopting Artificial Intelligence. This Specialization from Laurence Moroney and Andrew Ng will help you develop and deploy machine learning models across any device or platform faster and more accurately than ever.
This Specialization builds upon skills learned in the TensorFlow in Practice Specialization. We recommend learners complete that Specialization prior to enrolling in TensorFlow: Data and Deployment.
Frequently Asked Questions
When will I have access to the lectures and assignments?
Once you enroll for a Certificate, you’ll have access to all videos, quizzes, and programming assignments (if applicable). Peer review assignments can only be submitted and reviewed once your session has begun. If you choose to explore the course without purchasing, you may not be able to access certain assignments.
What will I get if I subscribe to this Specialization?
When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.
What is the refund policy?
Is financial aid available?
More questions? Visit the Learner Help Center.
