Thesis Details

Generování obličejů s pomocí podmíněných generativních neuronových sítí

Bachelor's Thesis Student: Venkrbec Tomáš Academic Year: 2019/2020 Supervisor: Kolář Martin, Ph.D.
English title
Generating Faces with Conditional Generative Adversarial Networks
Language
Czech
Abstract

The main goal of this thesis is to implement and compare models based on various architectures of conditional generative adversarial networks. Their main purpose is to conditionally generate realistic looking human faces with selected features. Results from models using DCGAN, WGAN-GP and ProGAN architectures were compared. Models were implemented using Tensorflow library and were trained on Flickr-Faces-HQ dataset. Across all used architectures, I managed to train models capable of generating realistic human faces, with an option to select age and gender.

Keywords

conditional generative adversarial networks, neural networks, generating faces, deep learning, machine learning, artificial intelligence

Department
Department of Computer Graphics and Multimedia FIT BUT
Degree Programme
Information Technology
Files
Status
defended, grade A
Date
13 July 2020
Reviewer
Hradiš Michal, Ing., Ph.D.
Committee
Zbořil František, doc. Ing., Ph.D. (DITS FIT BUT), předseda
Grégr Matěj, Ing., Ph.D. (DIFS FIT BUT), člen
Hradiš Michal, Ing., Ph.D. (DCGM FIT BUT), člen
Kekely Lukáš, Ing., Ph.D. (DCSY FIT BUT), člen
Rogalewicz Adam, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Citation
VENKRBEC, Tomáš. Generování obličejů s pomocí podmíněných generativních neuronových sítí. Brno, 2020. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2020-07-13. Supervised by Kolář Martin. Available from: https://www.fit.vut.cz/study/thesis/22869/
BibTeX 
@bachelorsthesis{FITBT22869,
    author = "Tom\'{a}\v{s} Venkrbec",
    type = "Bachelor's thesis",
    title = "Generov\'{a}n\'{i} obli\v{c}ej\r{u} s pomoc\'{i} podm\'{i}n\v{e}n\'{y}ch generativn\'{i}ch neuronov\'{y}ch s\'{i}t\'{i}",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2020,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/22869/"
}

Theses

Back to top