Application of mi based prediction of the deep learning cnn model to enhancement and Scheduling the gpu utilization of the ds

Document Type : Primary Research paper

Authors

1 Associate Professor, Department of Computer Science and Engineering, Mailam Engineering College

2 PG Scholar, Department of Computer Science and Engineering, Mailam Engineering Collegz

3 Assistant Professor, Department of Computer Science and Engineering, Mailam Engineering College

Abstract

A segmentation process involves labeling an image or images to obtain more meaningful information. On biomedical images, this activity plays an important role in helping the pathologist to carry out in-depth analyses. After the introduction of Graphics Processing Unit (GPU) not only for necessary graphics but also for goal calculation, the segmentation process which is computationally expensive can potentially be improved. The good accuracy of the detection and segmentation result provides morphological information to the pathologist. As a result, more approaches have been developed to ensure good detection and segmentation performance such as deep learning approach. Convolutional Neural Network (CNN) is one of the deep learning architectures with complex computation. This article presents an overview of the use of CNN as an important deep learning architecture under the GPU platform and provides an approach for using GPUs as potential additional parallel techniques in CNN. Keywords: Image segmentation; deep learning; convolutional neural network; medical image, GPU speed
Int. J. of Aquatic Science
Volume 13, Issue 1 - Serial Number 1
January 2022
Pages 394-399

Files

Share

How to cite

Statistics