prikaz prve stranice dokumenta Prijenosno učenje neuronske mreže Xception za prepoznavanje pasmine pasa
No public access
undergraduate thesis
Prijenosno učenje neuronske mreže Xception za prepoznavanje pasmine pasa
2020. urn:nbn:hr:168:814421
Horvat Horetzky, Hana
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Horvat Horetzky, H. (2020). Prijenosno učenje neuronske mreže Xception za prepoznavanje pasmine pasa (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:814421

Horvat Horetzky, Hana. "Prijenosno učenje neuronske mreže Xception za prepoznavanje pasmine pasa." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:814421

Horvat Horetzky, Hana. "Prijenosno učenje neuronske mreže Xception za prepoznavanje pasmine pasa." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:814421

Horvat Horetzky, H. (2020). 'Prijenosno učenje neuronske mreže Xception za prepoznavanje pasmine pasa', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 18 October 2024, https://urn.nsk.hr/urn:nbn:hr:168:814421

Horvat Horetzky H. Prijenosno učenje neuronske mreže Xception za prepoznavanje pasmine pasa [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2024 October 18] Available at: https://urn.nsk.hr/urn:nbn:hr:168:814421

H. Horvat Horetzky, "Prijenosno učenje neuronske mreže Xception za prepoznavanje pasmine pasa", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:814421

Please login to the repository to save this object to your list.
Metadata
TitlePrijenosno učenje neuronske mreže Xception za prepoznavanje pasmine pasa
Title (english)Transfer Learning of an Xception Neural Network to Recognize Dog Breed
AuthorHana Horvat Horetzky
MentorTomislav Petković (mentor)
Committee memberTomislav Petković (predsjednik povjerenstva)
Committee memberMatea Đonlić (član povjerenstva)
Committee memberKristijan Bartol (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-09-15, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Cilj ovog rada je opisati strukturu i primjenu neuronskih mreža te tehniku prijenosnog učenja neuronskih mreža. U radu se opisuje arhitektura pretrenirane neuronske mreže Xception. Skup za učenje predstavlja skup fotografija pasa svrstanih u 180 kategorija prema pasmini pasa. Programskom izvedbom nastojala se istrenirati neuronska mreža temeljena na Xception arhitekturi dovoljno dobro da bi se pomoću nje moglo identificirati kojoj pasmini psa pripada pas na promatranoj fotografiji.
Abstract (english)
The aim of this thesis is to describe the structure and applications of neural networks and the technique of transfer learning. This thesis describes the architecture of the pretrained neural network Xception. The learning set represents photographs of dogs classified in 180 categories according to the dog breed. A computer program was used to train the neural network based on the Xception architecture sufficiently well that it can be used to identify which breed the dog in the observed photo belongs to.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:814421
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 on2022-12-28 09:10:56