Transfer Learning Based Automatic Model Creation Tool For Resource Constraint Devices

TL;DR

This paper introduces a transfer learning-based tool that automatically creates machine learning models for resource-constrained devices, simplifying model development without coding and demonstrating effectiveness on image and audio classification tasks.

Contribution

The paper presents a novel automatic model creation tool leveraging transfer learning for resource-limited devices, with architecture and experimental validation included.

Findings

Achieved high accuracy on Stanford Cars and ESC-50 datasets.

Demonstrated reduced memory footprint suitable for constrained devices.

Validated effectiveness of pretrained models YAMNet and MobileNetV2.

Abstract

With the enhancement of Machine Learning, many tools are being designed to assist developers to easily create their Machine Learning models. In this paper, we propose a novel method for auto creation of such custom models for constraint devices using transfer learning without the need to write any machine learning code. We share the architecture of our automatic model creation tool and the CNN Model created by it using pretrained models such as YAMNet and MobileNetV2 as feature extractors. Finally, we demonstrate accuracy and memory footprint of the model created from the tool by creating an Automatic Image and Audio classifier and report the results of our experiments using Stanford Cars and ESC-50 dataset.