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)

Generating C code with TVM

Compiling the TFLite model to C code is straightforward with TVM. TVM only needs an input model, a target device, and a single command line to generate a TAR package with the generated C code.

In this recipe, we will show how to convert a pretrained CIFAR-10 model into C code with microTVM, an extension of TVM for microcontroller deployment.

The following Bash script contains the commands referred to in this recipe:

  • compile_model_microtvm.sh:

https://github.com/PacktPublishing/TinyML-Cookbook/blob/main/Chapter08/BashScripts/compile_model_microtvm.sh

Getting ready

In this section, we will examine how TVM can generate C code and explain what microTVM is.

TVM is a DL compiler technology that we can use in Python and in the same environment where we build, train, and quantize the model with TFLite. Although TVM natively offers a Python API, there is an alternative and more straightforward API that is based on a command-line interface...