prikaz prve stranice dokumenta Konvolucijski modeli za jednooku predikciju dubine scene
No public access
undergraduate thesis
Konvolucijski modeli za jednooku predikciju dubine scene
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. urn:nbn:hr:168:434533
Oreč, Filip
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Oreč, F. (2019). Konvolucijski modeli za jednooku predikciju dubine scene (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:434533

Oreč, Filip. "Konvolucijski modeli za jednooku predikciju dubine scene." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:434533

Oreč, Filip. "Konvolucijski modeli za jednooku predikciju dubine scene." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:434533

Oreč, F. (2019). 'Konvolucijski modeli za jednooku predikciju dubine scene', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 16 July 2024, https://urn.nsk.hr/urn:nbn:hr:168:434533

Oreč F. Konvolucijski modeli za jednooku predikciju dubine scene [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2019 [cited 2024 July 16] Available at: https://urn.nsk.hr/urn:nbn:hr:168:434533

F. Oreč, "Konvolucijski modeli za jednooku predikciju dubine scene", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:168:434533

Metadata
TitleKonvolucijski modeli za jednooku predikciju dubine scene
Title (english)Convolutional Models for Monocular Depth Prediction
AuthorFilip Oreč
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberPetra Bevandić (član povjerenstva)
Committee memberIvan Grubišić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2019-09-10, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Rad opisuje općenito neuronske mreže, a posebno konvolucijske neuronske mreže. Opisan je način učenja neuronske mreže algoritmom gradijentnog spusta. U radu se također opisuju rezidualne neuronske mreže. Programski je implementiran i evaluiran konvolucijski model za jednooku predikciju dubine scene koji se temelji na konkret- noj implementaciji rezidualnih neuronskih mreža, ResNet50. Na kraju su prikazani rezultati.
Abstract (english)
Paper desribes generally neural networks, especially the convolutional neural networks. The neural network learning method by gradient descent algorithm is described. This paper also also describes residual neuronal networks. Convolutional model for mo- nocular depth prediction that is based on concrete implementation of resiudal neural network, ResNet50, is implemented and evaluated. Lastly, the results are presented.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:434533
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 on2020-01-07 20:49:58