Book Image

TinyML Cookbook

By : Gian Marco Iodice
Book Image

TinyML Cookbook

By: Gian Marco Iodice

Overview of this book

This book explores TinyML, a fast-growing field at the unique intersection of machine learning and embedded systems to make AI ubiquitous with extremely low-powered devices such as microcontrollers. The TinyML Cookbook starts with a practical introduction to this multidisciplinary field to get you up to speed with some of the fundamentals for deploying intelligent applications on Arduino Nano 33 BLE Sense and Raspberry Pi Pico. As you progress, you’ll tackle various problems that you may encounter while prototyping microcontrollers, such as controlling the LED state with GPIO and a push-button, supplying power to microcontrollers with batteries, and more. Next, you’ll cover recipes relating to temperature, humidity, and the three “V” sensors (Voice, Vision, and Vibration) to gain the necessary skills to implement end-to-end smart applications in different scenarios. Later, you’ll learn best practices for building tiny models for memory-constrained microcontrollers. Finally, you’ll explore two of the most recent technologies, microTVM and microNPU that will help you step up your TinyML game. By the end of this book, you’ll be well-versed with best practices and machine learning frameworks to develop ML apps easily on microcontrollers and have a clear understanding of the key aspects to consider during the development phase.
Table of Contents (10 chapters)

Evaluating the accuracy of the TFLite model

The tiny model just trained can classify the 10 classes of CIFAR-10 with an accuracy of 73%. However, what is the model's accuracy of the quantized variant generated by the TFLite converter?

In this recipe, we will quantize the model with the TFLite converter and show how to perform this accuracy evaluation on the test dataset with the TFLite Python interpreter. After the accuracy evaluation, we will convert the TFLite model to a C-byte array.

The following Colab file (the Evaluating the accuracy of the quantized model section) contains the code referred to in this recipe:

  • prepare_model.ipynb:

https://github.com/PacktPublishing/TinyML-Cookbook/blob/main/Chapter07/ColabNotebooks/prepare_model.ipynb.

Getting ready

In this section, we will explain why the accuracy of the TFLite model may differ from the trained one.

As we know, the trained model needs to be converted to a more compact and lightweight representation...