prikaz prve stranice dokumenta Generiranje slika lica generativnim suparničkim mrežama
No public access
master's thesis
Generiranje slika lica generativnim suparničkim mrežama
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. urn:nbn:hr:168:801506
Macuka, Mihael
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Macuka, M. (2021). Generiranje slika lica generativnim suparničkim mrežama (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:801506

Macuka, Mihael. "Generiranje slika lica generativnim suparničkim mrežama." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:801506

Macuka, Mihael. "Generiranje slika lica generativnim suparničkim mrežama." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:801506

Macuka, M. (2021). 'Generiranje slika lica generativnim suparničkim mrežama', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 27 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:801506

Macuka M. Generiranje slika lica generativnim suparničkim mrežama [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2021 [cited 2024 December 27] Available at: https://urn.nsk.hr/urn:nbn:hr:168:801506

M. Macuka, "Generiranje slika lica generativnim suparničkim mrežama", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:168:801506

Metadata
TitleGeneriranje slika lica generativnim suparničkim mrežama
Title (english)Generating Face Images Using Generative Adversarial Networks
AuthorMihael Macuka
MentorZoran Kalafatić (mentor)
Committee memberZoran Kalafatić (predsjednik povjerenstva)
Committee memberTomislav Hrkać (član povjerenstva)
Committee memberMarko Čupić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2021-07-07, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Generativne suparničke mreže generativni su modeli dubokog učenja. U ovom je radu prikazana njihova primjena na problemu generiranja ljudskih lica. Pomoću programskog jezika Python, PyTorcha i ostalih biblioteka napravljena je implementacija neuronskih mreža. Implementacija je isprobana na dostupnim skupovima za treniranja UTKFace i CelebA. Priloženi su rezultati generiranja kao i prikazi pogreške tijekom treniranja. Takod̄er, rezultati su uspored̄eni s dvije javno dostupne implementacije na GitHub servisu.
Abstract (english)
Generative Adversarial Networks are deep learning generative models. In this master thesis, face generating usage is shown. Neural network implementation is developed with programming language Python, PyTorch, and additional libraries. Implementation is tested on publicly available datasets UTKFace and CelebA. Generated samples, as well as loss function plots, are provided. Also, generated results are compared with two publicly available implementations on GitHub.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:801506
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 15:27:48