Generiranje slika generativnim suparničkim mrežama

master's thesis

• Title (english): Generating Images Using Generative Adversarial Networks
• Author: Mirko Bartol
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Tomislav Hrkać (član povjerenstva)
• Committee member: Siniša Šegvić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu su objašnjene neuronske mreže, konvolucijske neuronske mreže i generativne suparničke mreže. Cilj je generiranje slika u boji korištenjem ACGAN-a. Koristimo konvolucijske neuronske mreže za učenje na slikama u obliku generativne suparničke mreže s pomoćnim klasifikatorom. Slike su dio CIFAR-10 baze podataka.

Abstract (english)

In this thesis, neural networks, convolutional neural networks, and generative adversarial networks are explained. The goal is to generate images in color using ACGAN. We use convolutional neural networks for image learning in the form of a auxiliary classifier generative adversarial network. The images are part of the CIFAR-10 database.

• Keywords: umjetna inteligencija; ACGAN; CIFAR-10; strojno učenje; generiranje slika; umjetne neuronske mreže; konvolucijske neuronske mreže
• Keywords (english): artificial intelligence; ACGAN; CIFAR-10; machine learning; image generation; artificial neural networks; convolutional neural networks
• Language: croatian
• URN:NBN: urn:nbn:hr:168:961539
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 09:44:34