Assessing the Efficacy of TinyML Implementations on STM32 Microcontrollers: A Performance Evaluation Study

In recent years, there has been a growing need for efficient deployment of deep learning models on resource-limited edge devices. This trend has prompted the development of NVIDIA's TAO Toolkit and TensorFlow Lite Micro framework as promising solutions for running deep-learning models on STM32...

Full description

Saved in:
Bibliographic Details
Published in:International Conference on Advanced Technologies for Signal and Image Processing (Online) Vol. 1; pp. 267 - 271
Main Authors: Ali, Diouani, Ridha, El Hamdi, Mohamed, Njah
Format: Conference Proceeding
Language:English
Published: IEEE 11.07.2024
Subjects:
Accuracy
Analytical models
Computational modeling
Deep learning
Deep Learning Models
Microcontrollers
Model Optimization
NVIDIA's TAO Toolkit
Performance evaluation
Resource-limited Edge Devices
STM32 Microcontrollers
TensorFlow Lite Micro
Tiny machine learning
ISSN:2687-878X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, there has been a growing need for efficient deployment of deep learning models on resource-limited edge devices. This trend has prompted the development of NVIDIA's TAO Toolkit and TensorFlow Lite Micro framework as promising solutions for running deep-learning models on STM32 microcontrollers. This paper presents a comparative study between these two tools, aiming to evaluate their performance, resource usage, and ease of deployment. By delving into their respective strengths and limitations, we seek to provide insights into the best practices for optimizing deep learning models in edge computing scenarios. Through empirical analysis, we assess the impact of model optimization techniques on classification accuracy, memory usage, and computational efficiency. Our findings reveal trade-offs between model complexity and resource consumption, shedding light on the strengths and limitations of each tool. Additionally, we explore the feasibility of deploying optimized models on STM32 microcontrollers using the STM32Cube.AI Developer Cloud platform. Insights from this study contribute to the advancement of efficient edge AI solutions by providing guidance on selecting appropriate optimization tools for specific deployment scenarios.
ISSN:2687-878X
DOI:10.1109/ATSIP62566.2024.10638900