Chapter 7: Running a Tiny CIFAR-10 Model on a Virtual Platform with the Zephyr OS

Prototyping a TinyML application directly on a physical device is really fun because we can instantly see our ideas at work in something that looks and feels like the real thing. However, before any application comes to life, we need to ensure that the models work as expected and, possibly, among different devices. Testing and debugging applications directly on microcontroller boards often requires a lot of development time. The main reason for this is the necessity to upload a program into a device for every change in code. However, virtual platforms can come in handy to make testing more straightforward and faster.

In this chapter, we will build an image classification application with TensorFlow Lite for Microcontrollers (TFLu) for an emulated Arm Cortex-M3 microcontroller. We will start by installing the Zephyr OS, the primary framework used in this chapter to accomplish our task. Next, we will...