The State of the Art when using GPUs in Devising Image Generation Methods Using Deep Learning

TL;DR

This paper analyzes GPU performance in deep learning-based image generation, highlighting how image size impacts processing time and suggesting improvements for handling high-resolution images in neural network applications.

Contribution

It provides a comparative analysis of GPU and CPU performance in image synthesis models and discusses the need for optimized computation for ultra-high-resolution images.

Findings

GPU processing time remains stable for small images but increases significantly for larger ones.

Processing limitations occur at 512 pixels, indicating a need for improved vector computation.

Parallel computation is essential for high-resolution image generation.

Abstract

Deep learning is a technique for machine learning using multi-layer neural networks. It has been used for image synthesis and image recognition, but in recent years, it has also been used for various social detection and social labeling. In this analysis, we compared (1) the number of Iterations per minute between the GPU and CPU when using the VGG model and the NIN model, and (2) the number of Iterations per minute by the number of pixels when using the VGG model, using an image with 128 pixels. When the number of pixels was 64 or 128, the processing time was almost the same when using the GPU, but when the number of pixels was changed to 256, the number of iterations per minute decreased and the processing time increased by about three times. In this case study, since the number of pixels becomes core dumping when the number of pixels is 512 or more, we can consider that we should consider improvement in the vector calculation part. If we aim to achieve 8K highly saturated computer graphics using neural networks, we will need to consider an environment that allows computation even when the size of the image becomes even more highly saturated and massive, and parallel computation when performing image recognition and tuning.