Thesis Details

Prořezávání hlubokých neuronových sítí pro rozpoznávání textu

Bachelor's Thesis Student: Petráš Simon Academic Year: 2021/2022 Supervisor: Kišš Martin, Ing.
English title
Deep Neural Network Pruning for Text Recognition
Language
Czech
Abstract

This document is a work on pruning neural network for handwriting recognition. The aim of the work is to create a program for pruning the network. We prune two types of neural networks, namely convolutional and recurrent neural networks. During the pruning of the convolution part, various criteria of parameter selection were experimented with. The result of the work is a model that achieves 20% acceleration while increasing the network inaccuracy by only 0.4%, but also a number of other models that are faster but also acquire higher inaccuracies.

Keywords

Neural networks, CNN, RNN, Pytorch, OCR, pruning

Department
Degree Programme
Files
Status
defended, grade C
Date
14 June 2022
Reviewer
Committee
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT), předseda
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Martínek Tomáš, Ing., Ph.D. (DCSY FIT BUT), člen
Matoušek Petr, doc. Ing., Ph.D., M.A. (DIFS FIT BUT), člen
Citation
PETRÁŠ, Simon. Prořezávání hlubokých neuronových sítí pro rozpoznávání textu. Brno, 2022. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2022-06-14. Supervised by Kišš Martin. Available from: https://www.fit.vut.cz/study/thesis/24873/
BibTeX
@bachelorsthesis{FITBT24873,
    author = "Simon Petr\'{a}\v{s}",
    type = "Bachelor's thesis",
    title = "Pro\v{r}ez\'{a}v\'{a}n\'{i} hlubok\'{y}ch neuronov\'{y}ch s\'{i}t\'{i} pro rozpozn\'{a}v\'{a}n\'{i} textu",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2022,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/24873/"
}
Back to top