Performance Analysis of Different Optimizers, Batch Sizes, and Epochs on Convolutional Neural Network for Image Classification

• Published in: Journal of Agriculture & Life Science Vol. 55; no. 2; pp. 99 - 107
• Main Authors: Sihalath, Thavisack, Basak, Jayanta Kumar, Bhujel, Anil, Arulmozhi, Elanchezhian, Moon, Byeong-Eun, Kim, Na-Eun, Lee, Doeg-Hyun, Kim, Hyeon-Tae
• Format: Journal Article
• Language: English
• Published: 경상국립대학교 농업생명과학연구원 30.04.2021; 농업생명과학연구원
• Subjects: 자연과학일반; Image Classification; Convolutional Neural Network; Epoch; Optimizer; Batch Size
• ISSN: 1598-5504; 2383-8272
• DOI: 10.14397/jals.2021.55.2.99

The important thing in the field of deep learning is to find out the appropriate hyper-parameter for image classification. In this study, the main objective is to investigate the performance of various hyper-parameters in a convolutional neural network model based on the image classification problem...

Table of Contents:

• Abstract Introduction Materials and Methods 1. Experiment 2. Batch Size and Epoch 3. Loss function evaluation criteria Results and Discussion 1. Loss evaluation 2. Accuracy evaluation 3. Performance of increasing batch size and poch References