prikaz prve stranice dokumenta Semantička segmentacija slika dubokim konvolucijskim modelima
No public access
undergraduate thesis
Semantička segmentacija slika dubokim konvolucijskim modelima
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:095033
Anđelić, Antonio
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Anđelić, A. (2018). Semantička segmentacija slika dubokim konvolucijskim modelima (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:095033

Anđelić, Antonio. "Semantička segmentacija slika dubokim konvolucijskim modelima." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:095033

Anđelić, Antonio. "Semantička segmentacija slika dubokim konvolucijskim modelima." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:095033

Anđelić, A. (2018). 'Semantička segmentacija slika dubokim konvolucijskim modelima', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 23 July 2024, https://urn.nsk.hr/urn:nbn:hr:168:095033

Anđelić A. Semantička segmentacija slika dubokim konvolucijskim modelima [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 July 23] Available at: https://urn.nsk.hr/urn:nbn:hr:168:095033

A. Anđelić, "Semantička segmentacija slika dubokim konvolucijskim modelima", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:095033

Metadata
TitleSemantička segmentacija slika dubokim konvolucijskim modelima
Title (english)Semantic Segmentation With Deep Convolutional Models
AuthorAntonio Anđelić
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberIvan Krešo (član povjerenstva)
Committee memberMarin Oršić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu su opisane neuronske mreže s posebnim naglaskom na konvolucijske mreže. Opisani su razni dijelovi i tehnike korištene u izgradnji i učenju neuronskih mreža. Rad također opisuje rezidualne neuronske mreže kao i njihovu konkretnu implementaciju, ResNet50. Programski je implementiran i evaluiran model za semantičku segmentaciju dobiven arhitekturom ResNet50. Rezultati su prikazani i komentirani na kraju rada.
Abstract (english)
This paper describes neural networks with focus on deep convolutional neural networks. Different parts and techniques used in neural networks are described. Also, paper describes residual neural network as well as its concrete implementation, ResNet50. Paper contains details about the implementaion of the system for semantic segmentation using ResNet50. Lastly, the results are presented.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:095033
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2019-03-13 18:36:52