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

Quantizing the model with the TensorFlow Lite converter

The TensorFlow model produced in the previous recipe is well suited for sharing or resuming training sessions. However, the model cannot be used for a microcontroller deployment because of its high memory requirements, which are mainly due to the following reasons:

The weights are stored in floating-point format
It keeps information that’s not required for the inference

Since our target device has computational and memory constraints, it is crucial to transform the trained model into something more compact.

This recipe will teach you how to convert the trained model into a lightweight format with the help of TensorFlow Lite and post-training integer 8-bit quantization.

Getting ready

TensorFlow Lite and post-training integer 8-bit quantization are the main ingredients that make the trained model suitable for inference on devices with reduced memory computational capabilities...