| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Prepoznavanje pasem psov s pomočjo globokega učenja : diplomsko delo
Authors:ID Rupnik, Minea (Author)
ID Fister, Iztok (Mentor) More about this mentor... New window
ID Vrbančič, Grega (Comentor)
Files:.pdf VS_Rupnik_Minea_2025.pdf (3,51 MB)
MD5: 0CD77E6F8A86FF3AB3F52A270881C96D
 
Language:Slovenian
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V diplomskem delu obravnavamo problem prepoznavanja pasem psov iz slik. Naš cilj je bil zasnovati in implementirati model z uporabo globokega učenja, ter pri tem doseči visoko napovedno uspešnost modela pri klasifikaciji pasem. Diplomsko delo zajema teoretične osnove strojnega učenja, podroben opis globokega učenja ter uporabljene arhitekture nevronskih mrež, kot tudi osnove uporabljenega programskega jezika Python in njegovih knjižnic. V praktičnem delu smo implementirali rešitev, kjer smo preizkusili različne arhitekture in analizirali njihovo učinkovitost.
Keywords:strojno učenje, globoko učenje, nevronske mreže, prenos znanja, Python
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[M. Rupnik]
Year of publishing:2025
Number of pages:1 spletni vir (1 datoteka PDF (X, 63 f.))
PID:20.500.12556/DKUM-92544 New window
UDC:004.932:004.85(043.2)
COBISS.SI-ID:238794499 New window
Publication date in DKUM:03.06.2025
Views:0
Downloads:14
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share


Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-ND 4.0, Creative Commons Attribution-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nd/4.0/
Description:Under the NoDerivatives Creative Commons license one can take a work released under this license and re-distribute it, but it cannot be shared with others in adapted form, and credit must be provided to the author.
Licensing start date:17.04.2025

Secondary language

Language:English
Title:Dog breed recognition using deep learning
Abstract:In this thesis, we addressed the problem of dog breed recognition from images. Our goal was to design and implement a model using deep learning to achieve high predictive performance for the task of breed classification. The thesis covers the theoretical foundations of machine learning, a detailed description of deep learning and neural network architectures used, as well as the basics of the Python programming language and its libraries. In the practical part, we implemented a solution where we tested various architectures and analyzed their efficiency.
Keywords:machine learning, deep learning, neural networks, transfer learning, Python


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica