Cargando…

Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network

In this paper, we present an analysis of important aspects that arise during the development of neural network applications. Our aim is to determine if the choice of library can impact the system’s overall performance, either during training or design, and to extract a set of criteria that could be...

Descripción completa

Detalles Bibliográficos
Autores principales: Novac, Ovidiu-Constantin, Chirodea, Mihai Cristian, Novac, Cornelia Mihaela, Bizon, Nicu, Oproescu, Mihai, Stan, Ovidiu Petru, Gordan, Cornelia Emilia
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9699128/
https://www.ncbi.nlm.nih.gov/pubmed/36433470
http://dx.doi.org/10.3390/s22228872
_version_ 1784838995068321792
author Novac, Ovidiu-Constantin
Chirodea, Mihai Cristian
Novac, Cornelia Mihaela
Bizon, Nicu
Oproescu, Mihai
Stan, Ovidiu Petru
Gordan, Cornelia Emilia
author_facet Novac, Ovidiu-Constantin
Chirodea, Mihai Cristian
Novac, Cornelia Mihaela
Bizon, Nicu
Oproescu, Mihai
Stan, Ovidiu Petru
Gordan, Cornelia Emilia
author_sort Novac, Ovidiu-Constantin
collection PubMed
description In this paper, we present an analysis of important aspects that arise during the development of neural network applications. Our aim is to determine if the choice of library can impact the system’s overall performance, either during training or design, and to extract a set of criteria that could be used to highlight the advantages and disadvantages of each library under consideration. To do so, we first extracted the previously mentioned aspects by comparing two of the most popular neural network libraries—PyTorch and TensorFlow—and then we performed an analysis on the obtained results, with the intent of determining if our initial hypothesis was correct. In the end, the results of the analysis are gathered, and an overall picture of what tasks are better suited for what library is presented.
format Online
Article
Text
id pubmed-9699128
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96991282022-11-26 Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network Novac, Ovidiu-Constantin Chirodea, Mihai Cristian Novac, Cornelia Mihaela Bizon, Nicu Oproescu, Mihai Stan, Ovidiu Petru Gordan, Cornelia Emilia Sensors (Basel) Article In this paper, we present an analysis of important aspects that arise during the development of neural network applications. Our aim is to determine if the choice of library can impact the system’s overall performance, either during training or design, and to extract a set of criteria that could be used to highlight the advantages and disadvantages of each library under consideration. To do so, we first extracted the previously mentioned aspects by comparing two of the most popular neural network libraries—PyTorch and TensorFlow—and then we performed an analysis on the obtained results, with the intent of determining if our initial hypothesis was correct. In the end, the results of the analysis are gathered, and an overall picture of what tasks are better suited for what library is presented. MDPI 2022-11-16 /pmc/articles/PMC9699128/ /pubmed/36433470 http://dx.doi.org/10.3390/s22228872 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Novac, Ovidiu-Constantin
Chirodea, Mihai Cristian
Novac, Cornelia Mihaela
Bizon, Nicu
Oproescu, Mihai
Stan, Ovidiu Petru
Gordan, Cornelia Emilia
Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network
title Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network
title_full Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network
title_fullStr Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network
title_full_unstemmed Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network
title_short Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network
title_sort analysis of the application efficiency of tensorflow and pytorch in convolutional neural network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9699128/
https://www.ncbi.nlm.nih.gov/pubmed/36433470
http://dx.doi.org/10.3390/s22228872
work_keys_str_mv AT novacovidiuconstantin analysisoftheapplicationefficiencyoftensorflowandpytorchinconvolutionalneuralnetwork
AT chirodeamihaicristian analysisoftheapplicationefficiencyoftensorflowandpytorchinconvolutionalneuralnetwork
AT novaccorneliamihaela analysisoftheapplicationefficiencyoftensorflowandpytorchinconvolutionalneuralnetwork
AT bizonnicu analysisoftheapplicationefficiencyoftensorflowandpytorchinconvolutionalneuralnetwork
AT oproescumihai analysisoftheapplicationefficiencyoftensorflowandpytorchinconvolutionalneuralnetwork
AT stanovidiupetru analysisoftheapplicationefficiencyoftensorflowandpytorchinconvolutionalneuralnetwork
AT gordancorneliaemilia analysisoftheapplicationefficiencyoftensorflowandpytorchinconvolutionalneuralnetwork