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

4.7
stars
569 ratings

Laurence Moroney

21,079 already enrolled

Offered By

TensorFlow: Data and Deployment SpecializationDeepLearning.AI

About this Course

11,237 recent views

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 second course teaches you how to run your machine learning models in mobile applications. You’ll learn how to prepare models for a lower-powered, battery-operated devices, then execute models on both Android and iOS platforms. Finally, you’ll explore how to deploy on embedded systems using TensorFlow on Raspberry Pi and microcontrollers.

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.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Shareable Certificate

Earn a Certificate upon completion

100% online

Start instantly and learn at your own schedule.

Course 2 of 4 in the

TensorFlow: Data and Deployment Specialization

Intermediate Level

Basic understanding of Kotlin and/or Swift

Approx. 11 hours to complete

English

What you will learn

Prepare models for battery-operated devices
Execute models on Android and iOS platforms
Deploy models on embedded systems like Raspberry Pi and microcontrollers

Skills you will gain

TensorFlow Lite
Mathematical Optimization
Machine Learning
Tensorflow
Object Detection

Flexible deadlines

Reset deadlines in accordance to your schedule.

Shareable Certificate

Earn a Certificate upon completion

100% online

Start instantly and learn at your own schedule.

Course 2 of 4 in the

TensorFlow: Data and Deployment Specialization

Intermediate Level

Basic understanding of Kotlin and/or Swift

Approx. 11 hours to complete

English

Instructor

Instructor rating

4.84/5 (68 Ratings)

Laurence Moroney

Instructor

Lead AI Advocate, Google

408,051 Learners

15 Courses

Offered by

DeepLearning.AI

Syllabus - What you will learn from this course

Content Rating96%(2,083 ratings)

Week

Week 1

6 hours to complete

Device-based models with TensorFlow Lite

Welcome to this course on TensorFlow Lite, an exciting technology that allows you to put your models directly and literally into people's hands. You'll start with a deep dive into the technology, and how it works, learning about how you can optimize your models for mobile use -- where battery power and processing power become an important factor. You'll then look at building applications on Android and iOS that use models, and you'll see how to use the TensorFlow Lite Interpreter in these environments. You'll wrap up the course with a look at embedded systems and microcontrollers, running your models on Raspberry Pi and SparkFun Edge boards.

6 hours to complete

14 videos (Total 40 min), 6 readings, 4 quizzes

14 videos

Introduction, A conversation with Andrew Ng5m

A few words from Laurence55s

Features and components of mobile AI2m

Architecture and performance3m

Optimization Techniques2m

Saving, converting, and optimizing a model3m

Examples2m

Quantization3m

TF-Select1m

Paths in Optimization1m

Running the models1m

Transfer learning3m

Converting a model to TFLite1m

Transfer learning with TFLite5m

6 readings

Prerequisites10m

Downloading the Ungraded Labs and Programming Assignments10m

GPU delegates10m

Learn about supported ops and TF-Select10m

Week 1 Wrap up1m

Exercise Description10m

1 practice exercise

Week 1 Quiz

Week

Week 2

1 hour to complete

Running a TF model in an Android App

Last week you learned about TensorFlow Lite and you saw how to convert your models from TensorFlow to TensorFlow Lite format. You also learned about the standalone TensorFlow Lite Interpreter which could be used to test these models. You wrapped with an exercise that converted a Fashion MNIST based model to TensorFlow Lite and then tested it with the interpreter.

This week you'll look at the first of the deployment types for this course: Android. Android is a versatile operating system that is used in a number of different device type, but most commonly phones, tablets and TV systems. Using TensorFlow Lite you can run your models on Android, so you can bring ML to any of these device types. While it helps to understand some Android programming concepts, we hope that you'll be able to follow along even if you don't, and at the very least try out the full sample apps that we'll explore for Image Classification, Object Detection and more!

1 hour to complete

15 videos (Total 36 min), 3 readings, 2 quizzes

15 videos

Introduction, A conversation with Andrew2m

Installation and resources2m

Architecture of a model1m

Initializing the Interpreter2m

Preparing the Input1m

Inference and results1m

Code walkthrough3m

Run the App2m

Classifying camera images55s

Initialize and prepare input3m

Demo of camera image classifier4m

Initialize model and prepare inputs1m

Inference and results3m

Demo of the object detection App1m

Code for the inference and results2m

3 readings

Android fundamentals and installation10m

Week 2 Wrap up10m

Description10m

1 practice exercise

Week 2 Quiz

Week

Week 3

2 hours to complete

Building the TensorFLow model on IOS

The other popular mobile operating system is, of course, iOS. So this week you'll do very similar tasks to last week -- learning how to take models and run them on iOS. You'll need some programming background with Swift for iOS to fully understand everything we go through, but even if you don't have this expertise, I think this weeks content is something you'll find fun to explore -- and you'll learn how to build a variety of ML applications that run on this important operating system!

2 hours to complete

22 videos (Total 45 min), 8 readings, 2 quizzes

22 videos

Introduction, A conversation with Andrew Ng54s

A few words from Laurence1m

What is Swift?45s

TensorFlowLiteSwift1m

Cats vs Dogs App1m

Taking the initial steps3m

Scaling the image2m

More steps in the process3m

Looking at the App in Xcode5m

What have we done so far and how do we continue?41s

Using the App50s

App architecture1m

Model details1m

Initial steps4m

Final steps1m

Looking at the code for the image classification App4m

Object classification intro30s

TFL detect App53s

App architecture55s

Initial steps58s

Final steps3m

Looking at the code for the object detection model3m

8 readings

Important links10m

Apple’s developer's site 10m

Apple's API10m

More details10m

Camera related functionalities10m

The Coco dataset10m

Week 3 Wrap up10m

Description10m

1 practice exercise

Week 3 Quiz

Week

Week 4

2 hours to complete

TensorFlow Lite on devices

Now that you've looked at TensorFlow Lite and explored building apps on Android and iOS that use it, the next and final step is to explore embedded systems like Raspberry Pi, and learn how to get your models running on that. The nice thing is that the Pi is a full Linux system, so it can run Python, allowing you to either use the full TensorFlow for Training and Inference, or just the Interpreter for Inference. I'd recommend the latter, as training on a Pi can be slow!

2 hours to complete

13 videos (Total 29 min), 7 readings, 2 quizzes

13 videos

Introduction, A conversation with Andrew Ng2m

A few words from Laurence3m

Devices3m

Starting to work on a Raspberry Pi1m

How do we start?2m

Image classification1m

The 4 step process2m

Object detection1m

Back to the 4 step process4m

Raspberry Pi demo2m

Microcontrollers2m

Closing words by Laurence28s

A conversation with Andrew Ng1m

7 readings

Edge TPU models10m

Options to choose from10m

Pre optimized mobileNet10m

Object detection model trained on the coco10m

Reviews

4.7

96 reviews

5 stars
77.23%
4 stars
16.63%
3 stars
4.55%
2 stars
0.87%
1 star
0.70%

TOP REVIEWS FROM DEVICE-BASED MODELS WITH TENSORFLOW LITE

by SRApr 14, 2020

It's a bit fast and definitely tightly packed. The objectives are clear though --how to build/debug/deploy on various modern devices (Android, iOS, RaspPi, etc)

by APMar 30, 2020

Was a great course.Had some hands on experience on codes using Gcollabs.Additionally helped me complete my project of deploying ML on android.

by GGNov 17, 2021

Perfect course to learn about TensorflowLite and deploying tflite models on various devices. Excellent instructor and course structure. This is one that I was looking for!

by PSMay 2, 2020

I am glad I did this course to learn about exciting options to run Tensorflow on a variety of devices. I am thinking about Raspberry Pi and iOS devices in particular

View all reviews

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. Looking for a place to start? Master the foundational basics of TensorFlow with the DeepLearning.AI TensorFlow Developer Professional Certificate. Looking to customize and build powerful real-world models for complex scenarios? Check out the TensorFlow: Advanced Techniques Specialization.

Frequently Asked Questions

When will I have access to the lectures and assignments?
Access to lectures and assignments depends on your type of enrollment. If you take a course in audit mode, you will be able to see most course materials for free. To access graded assignments and to earn a Certificate, you will need to purchase the Certificate experience, during or after your audit. If you don't see the audit option:
The course may not offer an audit option. You can try a Free Trial instead, or apply for Financial Aid.
The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
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.
Is financial aid available?
Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.

More questions? Visit the Learner Help Center.

Device-based Models with TensorFlow Lite

About this Course

What you will learn

Skills you will gain