prikaz prve stranice dokumenta Kvantizacija dubokih konvolucijskih modela
No public access
master's thesis
Kvantizacija dubokih konvolucijskih modela
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. urn:nbn:hr:168:565022
Oreč, Filip
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Oreč, F. (2021). Kvantizacija dubokih konvolucijskih modela (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:565022

Oreč, Filip. "Kvantizacija dubokih konvolucijskih modela." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:565022

Oreč, Filip. "Kvantizacija dubokih konvolucijskih modela." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:565022

Oreč, F. (2021). 'Kvantizacija dubokih konvolucijskih modela', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 26 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:565022

Oreč F. Kvantizacija dubokih konvolucijskih modela [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2021 [cited 2024 November 26] Available at: https://urn.nsk.hr/urn:nbn:hr:168:565022

F. Oreč, "Kvantizacija dubokih konvolucijskih modela", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:168:565022

Metadata
TitleKvantizacija dubokih konvolucijskih modela
Title (english)Quantization of deep convolutional models
AuthorFilip Oreč
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberMarko Čupić (član povjerenstva)
Committee memberVladimir Čeperić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2021-07-16, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj rad se bavi kvantiziranjem dubokih konvolucijskih modela. Svrha kvantizacije je provođenje izračuna u nižoj preciznosti kako bi se smanjilo vrijeme zaključivanja dubokog modela. Kvantiziran je model SwiftNet na problemu semantičke segmentacije. Za implementaciju korišten je okvir TensorRT, te je model kvantiziran za uređaj NVIDIA Jetson AGX Xavier. Pokazalo se kako kvantizirani modela ima puno manje vrijeme zaključivanja u odnosu na FP32 model uz minimalan gubitak točnosti, te nešto manje vrijeme zaključivanja nego FP16 model također uz minimalan gubitak točnosti.
Abstract (english)
The goal of this thesis is quantization of deep convolutional models. The goal of quantization is to use lower precision for computation which lowers inference time of the deep model. Model which is quantized in this thesis is SwiftNet model on the problem of semantic segmentation. For implementation TensorRT framework was used and models was quantized for the NVIDIA Jetson AGX Xavier embedded hardware. It has been shown that quantized model has much lower inference time than FP32 model with minimal accuracy loss and little lower inference time than FP16 model also with minimal accuracy loss.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:565022
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-13 15:45:01