prikaz prve stranice dokumenta Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython
  Preuzmi
PDF 1.58 MB
Znanstveni rad - Izvorni znanstveni rad
Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython
U: Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology. Tirana: University of Tirana, 2021. str. 67-73. urn:nbn:hr:112:223963
Đokić, Kristian; Mikolčević, Hrvoje; Radišić, Bojan

Citirajte ovaj rad

Đokić, K., Mikolčević, H. i Radišić, B. (2021). Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython. Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology (str. 67-73). Tirana: University of Tirana. Preuzeto s https://urn.nsk.hr/urn:nbn:hr:112:223963

Đokić, Kristian, et al. "Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython." Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology, University of Tirana, 2021, str. 67-73. https://urn.nsk.hr/urn:nbn:hr:112:223963

Đokić, Kristian, Hrvoje Mikolčević i Bojan Radišić. "Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython." U Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology, 67-73. Tirana: University of Tirana, 2021. Citirano 05.02.2025.. https://urn.nsk.hr/urn:nbn:hr:112:223963

Đokić, K., Mikolčević, H. i Radišić, B. (2021) 'Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython', Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology, University of Tirana, Tirana, str. 67-73. Preuzeto s: https://urn.nsk.hr/urn:nbn:hr:112:223963 (Datum pristupa: 05.02.2025.)

Đokić K, Mikolčević H, Radišić B. Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython. Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology. Tirana: University of Tirana; 2021. Str. 67-73. [pristupljeno 05.02.2025.] Dostupno na: https://urn.nsk.hr/urn:nbn:hr:112:223963

K. Đokić, H. Mikolčević i B. Radišić, "Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython", Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology Tirana: University of Tirana, 2021. [Online] Dostupno na: https://urn.nsk.hr/urn:nbn:hr:112:223963 [Citirano: 05.02.2025.]

Za citiranje koristite ovu mrežnu adresu: https://urn.nsk.hr/urn:nbn:hr:112:223963
Prijavite se u repozitorij kako biste mogli spremiti objekt u svoju listu.
Podaci o radu
Naslov (engleski)Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython
AutorKristian Đokić
AutorHrvoje Mikolčević
AutorBojan Radišić
Autorova ustanovaVeleučilište u Požegi
Znanstveno / umjetničko
područje, polje i grana		DRUŠTVENE ZNANOSTI
Informacijske i komunikacijske znanosti
Znanstveno / umjetničko
područje, polje i grana		TEHNIČKE ZNANOSTI
Računarstvo
Sažetak (engleski)
In recent years we have witnessed the rapid development of machine learning algorithms, and the same can be said for IoT. Developments in both fields have also influenced the growth of machine learning algorithms in IoT devices. The authors of a series of papers cite several reasons to argue this trend. This paper explores the possibility of using the Python programming language in different versions to create, train, and implement convolutional neural networks on two SoCs based on different architectures (ARM and RISC-V). The influence of the number of filters in the convolutional layer on the inference speed is also investigated. The number of filters has a different effect on inference speed depending on the existence of additional components that accelerate individual operations of convolutional neural networks (convolution, batch normalization, activation, and pooling operations).
Ključne riječi (engleski)
Jezikengleski
Vrsta publikacijeZnanstveni rad - Izvorni znanstveni rad
Status objaveObjavljen
Vrsta recenzijeRecenziran - međunarodna recenzija
Verzija publikacijeObjavljena verzija rada (izdavačev PDF)
Naslov zbornikaProceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology
Brojčani podacistr. 67-73
e-ISSN1613-0073
URN:NBNurn:nbn:hr:112:223963
Datum objave publikacije2021
SkupNaziv: 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology (CSIT 2021)
Lokacija: Tirana, Albanija
Datum početka: 2021-05-21
Datum završetka: 2021-05-22
Vrsta izlaganja: Predavanje
URL dokumentahttps://ceur-ws.org/Vol-2872/paper10.pdf
Vrsta resursaTekst
IzdavačUniversity of Tirana
Mjesto izdavanjaTirana
Prava pristupaOtvoreni pristup
Uvjeti korištenjaIkona licence Imenovanje 4.0 međunarodna (CC BY 4.0)
Datum i vrijeme pohrane2024-05-03 10:49:41