prikaz prve stranice dokumenta Stvaranje slika ljudskih lica primjenom generativnih suparničkih mreža
No public access
master's thesis
Stvaranje slika ljudskih lica primjenom generativnih suparničkih mreža
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. urn:nbn:hr:168:014345
Pokrivka, Petar
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Pokrivka, P. (2021). Stvaranje slika ljudskih lica primjenom generativnih suparničkih mreža (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:014345

Pokrivka, Petar. "Stvaranje slika ljudskih lica primjenom generativnih suparničkih mreža." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:014345

Pokrivka, Petar. "Stvaranje slika ljudskih lica primjenom generativnih suparničkih mreža." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:014345

Pokrivka, P. (2021). 'Stvaranje slika ljudskih lica primjenom generativnih suparničkih mreža', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 25 August 2024, https://urn.nsk.hr/urn:nbn:hr:168:014345

Pokrivka P. Stvaranje slika ljudskih lica primjenom generativnih suparničkih mreža [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2021 [cited 2024 August 25] Available at: https://urn.nsk.hr/urn:nbn:hr:168:014345

P. Pokrivka, "Stvaranje slika ljudskih lica primjenom generativnih suparničkih mreža", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:168:014345

Metadata
TitleStvaranje slika ljudskih lica primjenom generativnih suparničkih mreža
Title (english)Generation Human Face Images Using Generative Adversarial Networks
AuthorPetar Pokrivka
MentorGoran Delač (mentor)
Committee memberGoran Delač (predsjednik povjerenstva)
Committee memberMarin Šilić (član povjerenstva)
Committee memberKlemo Vladimir (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2021-09-16, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu su opisane umjetne neuronske mreže, objašnjeni načini učenja neuronski mreža te je dan uvid u aktivacijske funkcije koje se koriste u pojedinim čvorovima neuronskih mreža. Opisane su konvolucijske neuronske mreže te najvažniji pojmovi vezani uz neuronske mreže. Proučeni su i opisani generativni modeli strojnog učenja, gdje je poseban naglasak stavljen na modele zasnovane na generativno suparničkim mrežama. Model generativno suparničke neuronske mreže implementiran je u PyTorch radnom okviru. Model je treniran i testiran na skupu podataka FFHQ. Prikazani su primjeri generirani slika nakon treniranja generativno suparničke mreže.
Abstract (english)
This paper describes artificial neural networks, explains the ways of learning neural networks and gives an insight into the activation functions used in individual nodes of neural networks. Convolutional neural networks and the most important terms related to neural networks are described. Generative models of machine learning have been studied and described, with special emphasis on models based on generative adversarial networks. The generative adversarial neural network model is implemented in the PyTorch framework. The model was trained and tested on the FFHQ data set. Examples of images generated after training generative adversarial network are presented.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:014345
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-13 15:55:02