ImageNet Challenging Classification with the Raspberry Pi: An Incremental Local Stochastic Gradient Descent Algorithm

TL;DR

This paper introduces an incremental local stochastic gradient descent algorithm optimized for Raspberry Pi devices to classify large-scale ImageNet data efficiently, outperforming traditional methods in speed and accuracy.

Contribution

The paper presents a novel incremental local SGD algorithm tailored for edge devices like Raspberry Pi to handle large datasets effectively.

Findings

Faster classification on ImageNet with Raspberry Pi 4 compared to PC-based SVM.

Higher accuracy achieved with the incremental local SGD.

Efficient parallel learning using data partitioning with k-means.

Abstract

With rising powerful, low-cost embedded devices, the edge computing has become an increasingly popular choice. In this paper, we propose a new incremental local stochastic gradient descent (SGD) tailored on the Raspberry Pi to deal with large ImageNet ILSVRC 2010 dataset having 1,261,405 images with 1,000 classes. The local SGD splits the data block into $k$ partitions using $k$means algorithm and then it learns in the parallel way SGD models in each data partition to classify the data locally. The incremental local SGD sequentially loads small data blocks of the training dataset to learn local SGD models. The numerical test results on Imagenet dataset show that our incremental local SGD algorithm with the Raspberry Pi 4 is faster and more accurate than the state-of-the-art linear SVM run on a PC Intel(R) Core i7-4790 CPU, 3.6 GHz, 4 cores.