Device-based Models with TensorFlow Lite from Coursera

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.

What's inside

Syllabus

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. Don't worry if you don't have access to the hardware -- for the most part you'll be able to do everything in emulated environments. So, let's get started by looking at what TensorFlow is and how it works!

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!

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!

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!

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Offers hands-on labs and interactive materials for a better learning experience

Builds upon TensorFlow in Practice Specialization and Deep Learning Specialization, providing a solid foundation for learners with prior knowledge

Introduces TensorFlow Lite, a technology for deploying machine learning models on mobile devices

Provides instructions on preparing models for low-powered devices and executing them on Android and iOS platforms

Covers deployment on embedded systems using TensorFlow on Raspberry Pi and microcontrollers

Assumes prior knowledge in TensorFlow and neural networks, making it suitable for experienced learners

Reviews summary

Highly-rated tensorflow lite specialization

Learners say this specialization on TensorFlow Lite combines well-rounded content on deploying models on various devices, with strong introductory foundations for a journey into Deep Learning. It has an overall positive sentiment with learners finding it engaging, informative, and well-structured.

Introductory, yet Comprehensive material

"The course is straightforward and very useful. I learned many new concepts regarding Tensorflow Lite in devices."

"Really informative course on tf lite for beginners like me, it has given serious thoughts about the EDGEML field and opportunities"

Clear explanations, excellent demonstrations

"Laurence is a good teacher. His explanations are clear and to the point."

"Well delivered and very interesting course. The code examples and walkthroughs are amazing and help to get you trying this stuff yourself quickly."

Assumes advanced knowledge

"it requires advanced knowledge on app development, even though not mandatory to validate the course."

Lacks mandatory hands-on assignments

"I really loved the TensorFlow in Practice specialization and the first course of the TensorFlow Data and Deployment delivered by M. Moroney. This course is not at all at their level."

"This course is good as overview - theoretical. You go through all the important topics... But unfortunately all you need is to watch. No exercises you would really need to do in order to complete the course."

Career center

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

Machine Learning Engineer

Machine Learning Engineers are in high demand due to the increasing adoption of AI and machine learning technologies across various industries. This course can provide you with the necessary skills and knowledge to build and deploy machine learning models on mobile devices, which is a rapidly growing field. You will learn how to optimize models for mobile use, build Android and iOS apps that use machine learning models, and deploy models on embedded systems like Raspberry Pi. This course can help you build a solid foundation in mobile machine learning and prepare you for a successful career as a Machine Learning Engineer.

See salaries and explore the career path for Machine Learning Engineer

Mobile Application Developer

Mobile Application Developers are responsible for designing, developing, and maintaining mobile applications. This course can provide you with the skills and knowledge to build mobile applications that use machine learning models. You will learn how to integrate TensorFlow Lite into Android and iOS apps, and how to deploy machine learning models on mobile devices. This course can help you build a strong foundation in mobile application development and prepare you for a successful career as a Mobile Application Developer.

See salaries and explore the career path for Mobile Application Developer

Data Scientist

Data Scientists use data to solve business problems and make informed decisions. This course can provide you with the skills and knowledge to use machine learning models to analyze data and extract insights. You will learn how to prepare data for machine learning, build and train machine learning models, and deploy models on mobile devices. This course can help you build a strong foundation in data science and prepare you for a successful career as a Data Scientist.

See salaries and explore the career path for Data Scientist

Software Engineer

Software Engineers design, develop, and maintain software systems. This course can provide you with the skills and knowledge to build software systems that use machine learning models. You will learn how to integrate TensorFlow Lite into software systems, and how to deploy machine learning models on mobile devices. This course can help you build a strong foundation in software engineering and prepare you for a successful career as a Software Engineer.

See salaries and explore the career path for Software Engineer

Product Manager

Product Managers are responsible for managing the development and launch of new products. This course can provide you with the skills and knowledge to manage the development of machine learning-based products. You will learn how to identify market opportunities for machine learning, build a business case for machine learning products, and manage the development and launch of these products. This course can help you build a strong foundation in product management and prepare you for a successful career as a Product Manager.

See salaries and explore the career path for Product Manager

Business Analyst

Business Analysts identify and solve business problems. This course can provide you with the skills and knowledge to use machine learning to solve business problems. You will learn how to identify opportunities for machine learning, build business cases for machine learning solutions, and implement these solutions. This course can help you build a strong foundation in business analysis and prepare you for a successful career as a Business Analyst.

See salaries and explore the career path for Business Analyst

Data Analyst

Data Analysts analyze data to identify trends and patterns. This course can provide you with the skills and knowledge to use machine learning to analyze data. You will learn how to prepare data for machine learning, build and train machine learning models, and interpret the results of these models. This course can help you build a strong foundation in data analysis and prepare you for a successful career as a Data Analyst.

See salaries and explore the career path for Data Analyst

Machine Learning Researcher

Machine Learning Researchers develop new machine learning algorithms and techniques. This course can provide you with the skills and knowledge to conduct research in machine learning. You will learn about the latest advances in machine learning, and how to apply these advances to real-world problems. This course can help you build a strong foundation in machine learning research and prepare you for a successful career as a Machine Learning Researcher.

See salaries and explore the career path for Machine Learning Researcher

Artificial Intelligence Engineer

Artificial Intelligence Engineers design, develop, and maintain AI systems. This course can provide you with the skills and knowledge to build AI systems that use machine learning models. You will learn about the different types of AI systems, and how to apply machine learning to these systems. This course can help you build a strong foundation in AI engineering and prepare you for a successful career as an Artificial Intelligence Engineer.

See salaries and explore the career path for Artificial Intelligence Engineer

Computer Vision Engineer

Computer Vision Engineers design, develop, and maintain computer vision systems. This course can provide you with the skills and knowledge to build computer vision systems that use machine learning models. You will learn about the different types of computer vision systems, and how to apply machine learning to these systems. This course can help you build a strong foundation in computer vision engineering and prepare you for a successful career as a Computer Vision Engineer.

See salaries and explore the career path for Computer Vision Engineer

Natural Language Processing Engineer

Natural Language Processing Engineers design, develop, and maintain natural language processing systems. This course can provide you with the skills and knowledge to build natural language processing systems that use machine learning models. You will learn about the different types of natural language processing systems, and how to apply machine learning to these systems. This course can help you build a strong foundation in natural language processing engineering and prepare you for a successful career as a Natural Language Processing Engineer.

See salaries and explore the career path for Natural Language Processing Engineer

Robotics Engineer

Robotics Engineers design, develop, and maintain robots. This course can provide you with the skills and knowledge to build robots that use machine learning models. You will learn about the different types of robots, and how to apply machine learning to these robots. This course can help you build a strong foundation in robotics engineering and prepare you for a successful career as a Robotics Engineer.

See salaries and explore the career path for Robotics Engineer

Game Developer

Game Developers design, develop, and maintain video games. This course can provide you with the skills and knowledge to build video games that use machine learning models. You will learn about the different types of video games, and how to apply machine learning to these games. This course can help you build a strong foundation in game development and prepare you for a successful career as a Game Developer.

See salaries and explore the career path for Game Developer

Healthcare Data Analyst

Healthcare Data Analysts analyze data to identify trends and patterns in healthcare data. This course can provide you with the skills and knowledge to use machine learning to analyze healthcare data. You will learn how to prepare healthcare data for machine learning, build and train machine learning models, and interpret the results of these models. This course can help you build a strong foundation in healthcare data analysis and prepare you for a successful career as a Healthcare Data Analyst.

See salaries and explore the career path for Healthcare Data Analyst

Financial Analyst

Financial Analysts analyze financial data to identify trends and patterns. This course can provide you with the skills and knowledge to use machine learning to analyze financial data. You will learn how to prepare financial data for machine learning, build and train machine learning models, and interpret the results of these models. This course can help you build a strong foundation in financial analysis and prepare you for a successful career as a Financial Analyst.

See salaries and explore the career path for Financial Analyst