Abstract:
Recently, as IoT devices have become popular, research to perform deep learning in small devices such as micro-controllers has been attempted. Microcontrollers have very ...Show MoreMetadata
Abstract:
Recently, as IoT devices have become popular, research to perform deep learning in small devices such as micro-controllers has been attempted. Microcontrollers have very limited resources compared to edge devices such as mobiles. Therefore, in order to perform deep learning-based image classification in a microcontroller, an optimization technique considering HW constraints is required. To this end, in this paper, we present a method for light weighting a model so that it can be executed in a microcontroller, and a process for distributing the lightweight model to a microcontroller. Finally, it was confirmed that image classification can be performed in an actual microcontroller through STM32F746G-Discovery.
Published in: 2023 14th International Conference on Information and Communication Technology Convergence (ICTC)
Date of Conference: 11-13 October 2023
Date Added to IEEE Xplore: 23 January 2024
ISBN Information: