You're reading from TinyML Cookbook - Second Edition

Product type Book

Published in Nov 2023

Publisher Packt

ISBN-13 9781837637362

Pages 664 pages

Edition 2nd Edition

Languages

Concepts

Machine Learning

Author (1):

Gian Marco Iodice

Table of Contents (16) Chapters

Preface

1. Getting Ready to Unlock ML on Microcontrollers

2. Unleashing Your Creativity with Microcontrollers

3. Building a Weather Station with TensorFlow Lite for Microcontrollers

4. Using Edge Impulse and the Arduino Nano to Control LEDs with Voice Commands

5. Recognizing Music Genres with TensorFlow and the Raspberry Pi Pico – Part 1

6. Recognizing Music Genres with TensorFlow and the Raspberry Pi Pico – Part 2

7. Detecting Objects with Edge Impulse Using FOMO on the Raspberry Pi Pico

8. Classifying Desk Objects with TensorFlow and the Arduino Nano

9. Building a Gesture-Based Interface for YouTube Playback with Edge Impulse and the Raspberry Pi Pico

10. Deploying a CIFAR-10 Model for Memory-Constrained Devices with the Zephyr OS on QEMU

11. Running ML Models on Arduino and the Arm Ethos-U55 microNPU Using Apache TVM

12. Enabling Compelling tinyML Solutions with On-Device Learning and scikit-learn on the Arduino Nano and Raspberry Pi Pico

13. Conclusion

14. Other Books You May Enjoy

15. Index

Acquiring QQVGA images with the YCbCr422 color format

When compiling the previous sketch for the Arduino Nano, you may have noticed the following warning message in the IDE’s output log: Low memory available, stability may occur. This warning message appears because the QVGA image in the RGB565 color format requires a buffer of 153.6 KB, equivalent to roughly 60% of the available SRAM in the microcontroller.

In this recipe, we will show how to acquire an image at a lower resolution and use the YCbCr422 color format to reduce memory requirements, without compromising image quality.

Getting ready

Images are well known to require big chunks of memory, which might be a problem when dealing with microcontrollers.

Lowering the image resolution is a common practice to reduce the image memory size. Common image resolutions for microcontrollers are smaller than the QVGA (320x240) previously used, such as QQVGA (160x120) or QQQVGA (80x60...