prikaz prve stranice dokumenta Kvantiziranje dubokih konvolucijskih modela
No public access
undergraduate thesis
Kvantiziranje dubokih konvolucijskih modela
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. urn:nbn:hr:168:953732
Ćosić, Tomislav
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Ćosić, T. (2022). Kvantiziranje dubokih konvolucijskih modela (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:953732

Ćosić, Tomislav. "Kvantiziranje dubokih konvolucijskih modela." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:953732

Ćosić, Tomislav. "Kvantiziranje dubokih konvolucijskih modela." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:953732

Ćosić, T. (2022). 'Kvantiziranje dubokih konvolucijskih modela', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 30 June 2024, https://urn.nsk.hr/urn:nbn:hr:168:953732

Ćosić T. Kvantiziranje dubokih konvolucijskih modela [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2022 [cited 2024 June 30] Available at: https://urn.nsk.hr/urn:nbn:hr:168:953732

T. Ćosić, "Kvantiziranje dubokih konvolucijskih modela", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:168:953732

Metadata
TitleKvantiziranje dubokih konvolucijskih modela
Title (english)Quantization of deep convolutional models
AuthorTomislav Ćosić
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberIvan Grubišić (član povjerenstva)
Committee memberJosip Šarić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2022-07-06, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Duboki konvolucijski modeli danas su metoda izbora za mnoge zadatke računalnog vida. Međutim, njihova računska složenost isključuje mnoge zanimljive primjene u robotici i inteligentnom prometu. Taj problem možemo ublažiti zamjenom decimalnih računskih operacija odgovarajućim cjelobrojnim operacijama. U okviru rada, potrebno je upoznati se s konvolucijskim modelom ResNet-18. Istražiti postojeće pristupe za kvantiziranje težina dubokih modela. Odabrati slobodno dostupni skup slika te oblikovati podskupove za učenje, validaciju i testiranje. Oblikovati algoritme, validirati hiperparametre te uhodati učenje, validiranje i zaključivanje. Modificirati postupak učenja tako da na izlazu dobijemo kvantizirani model. Vrednovati naučene modele, prikazati postignutu točnost te provesti usporedbu s rezultatima iz literature. Komentirati učinkovitost učenja i zaključivanja. Predložiti pravce budućeg razvoja. Radu priložiti izvorni kod razvijenih postupaka uz potrebna objašnjenja i dokumentaciju. Citirati korištenu literaturu i navesti dobivenu pomoć.
Abstract (english)
Today, deep convolutional models are the method of choice for many tasks in computer vision. However, their computational complexity prevents many interesting applications in robotics and intelligent traffic. We can alleviate that problem by replacing floating-point operations with their corresponding integer counterparts. In the cope of this paper, it is necessary to introduce ourselves with the ResNet-18 convolutional model. Research existing approaches towards quantization of the weights in convolutional models. Select freely available dataset and form subsets for learning, validation and testing. Model the algorithm, validate hyperparameters and set up learning, validation and testing. Modify the learning procedure to get the quantized model as an output. Evaluate learned models, display acquired accuracy and compare the values with literature results. Comment on the efficiency of the learning and inference process. Suggest the directions of futher research. Attach the source code of developed procedure along with necessary explanations and documentation. Cite used literature and state received help.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:953732
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 on2023-01-15 09:57:05