Comparison of Neural Style Transfer Performance of Deep Learning Models

Basit Öğe Kaydı
dc.authoridKaradağ, Batuhan/0000-0002-4661-6607
dc.authorwosidKaradağ, Batuhan/AFC-2569-2022
dc.contributor.authorKaradag, Batuhan
dc.contributor.authorAri, Ali
dc.contributor.authorKaradag, Muge
dc.date.accessioned2024-08-04T20:11:43Z
dc.date.available2024-08-04T20:11:43Z
dc.date.issued2021
dc.departmentİnönü Üniversitesien_US
dc.description.abstractNeural style transfer is one of the most studied topics in both academic and industrial fields. Quality and performance enhancement are among the most targeted goals in the studies. In this study, the performance of different CNN models in neural style transfer was investigated. Deep features were obtained using VGG16, VGG19 and ResNet50 models. Thanks to these attributes, a new target image is created by taking the content of the content image and the style of the style image. Adam, RMSprop and SGD optimization algorithms are used. In neural transfer studies, the best visual performance was obtained from VGG19 network model by using SGD optimization algorithm. The fastest neural style transfer in terms of time was obtained using the SGD optimization algorithm in the ResNet50 convolutional neural network model.en_US
dc.identifier.doi10.2339/politeknik.885838
dc.identifier.endpage1622en_US
dc.identifier.issn1302-0900
dc.identifier.issn2147-9429
dc.identifier.issue4en_US
dc.identifier.startpage1611en_US
dc.identifier.trdizinid1235244en_US
dc.identifier.urihttps://doi.org/10.2339/politeknik.885838
dc.identifier.urihttps://search.trdizin.gov.tr/yayin/detay/1235244
dc.identifier.urihttps://hdl.handle.net/11616/92956
dc.identifier.volume24en_US
dc.identifier.wosWOS:000755415400002en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakTR-Dizinen_US
dc.language.isotren_US
dc.publisherGazi Univen_US
dc.relation.ispartofJournal of Polytechnic-Politeknik Dergisien_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectNeural style transferen_US
dc.subjectconvolutional neural networken_US
dc.subjectdeep convolutional neural networken_US
dc.titleComparison of Neural Style Transfer Performance of Deep Learning Modelsen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
TR-Dizin İndeksli Yayınlar Koleksiyonu