TinyML

Chapter 13. TensorFlow Lite for Microcontrollers

In this chapter we look at the software framework we’ve been using for all of the examples in the book: TensorFlow Lite for Microcontrollers. We go into a lot of detail, but you don’t need to understand everything we cover to use it in an application. If you’re not interested in what’s happening under the hood, feel free to skip this chapter; you can always return to it when you have questions. If you do want to better understand the tool you’re using to run machine learning, we cover the history and inner workings of the library here.

What Is TensorFlow Lite for Microcontrollers?

The first question you might ask is what the framework actually does. To understand that, it helps to break the (rather long) name down a bit and explain the components.

TensorFlow

You may well have heard of TensorFlow itself if you’ve looked into machine learning. TensorFlow is Google’s open source machine learning library, with the motto “An Open Source Machine Learning Framework for Everyone.” It was developed internally at Google and first released to the public in 2015. Since then a large external community has grown up around the software, with more contributors outside Google than inside. It’s aimed at Linux, Windows, and macOS desktop and server platforms and offers a lot of tools, examples, and optimizations around training and deploying models in the cloud. It’s the main machine learning library used within Google to power its products, and ...