20.500.12556/RUL-173253 End-to-End Deployment of Deep Learning Models for Image Classification on Embedded Systems with a Comparative Study of TensorFlow Lite and PyTorch-ONNX Workflows Celovita implementacija globokih nevronskih mrež za klasifikacijo slik na vgrajenih sistemih z uporabo TensorFlow Lite in PyTorch-ONNX This thesis examines the end-to-end deployment of deep learning models for image classification on the STM32H747I-Discovery board, a resource-constrained embedded system. A detailed comparative analysis of two deployment workflows is provided: one using TensorFlow with its native TFLite format and another using PyTorch with ONNX as an intermediate representation. The study documents the process from model training and quantization to on-device inference and evaluates the trade-offs in memory footprint, latency, and development complexity. The results show that the TensorFlow-to-TFLite workflow is a more efficient and streamlined solution for this application. It yields a model with significantly lower RAM usage and faster inference speed. This demonstrates the benefits of a specialized deployment format over a generalized one for memory-critical applications. Ta diplomska naloga obravnava celovit proces implementacije modelov globokega učenja za klasifikacijo slik na mikrokrmilniku z omejenimi viri STM32H747I-Discovery. V nalogi sta primerjana dva ključna pristopa: prvi temelji na ogrodju TensorFlow in formatu TFLite, drugi pa na ogrodju PyTorch in vmesnem formatu ONNX. Z natančno metodologijo in empirično analizo so predstavljene primerjave med porabo pomnilnika, hitrostjo inference in zahtevnostjo razvojnega procesa. Rezultati jasno kažejo, da je pristop s TensorFlow in TFLite učinkovitejši in zmogljivejši za ciljno strojno opremo, kar potrjuje prednosti uporabe specializiranih formatov za vgrajene sisteme. embedded system artificial intelligence edge computing TinyML STM32 vgrajen sistem umetna inteligenca robno računalništvo TinyML STM32 true false false Angleški jezik Slovenski jezik Diplomsko delo/naloga 2025-09-15 10:30:11 2025-09-15 10:30:15 2025-11-07 03:47:42 0000-00-00 00:00:00 2025 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 38288 253218563 Naumov_Angel_-_Celovita_implementacija_globokih_nevronskih_mrez_za_klasifikacijo_slik_na_vgrajen.pdf Naumov_Angel_-_Celovita_implementacija_globokih_nevronskih_mrez_za_klasifikacijo_slik_na_vgrajen.pdf 1 A0BFC071A0E4EC1BDF127EB67528AC98 452b12cada8a2cf80d3b4f209ba81a099f737e84805a601900714801023b8c87 08d77d10-920e-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=217460 Fakulteta za računalništvo in informatiko 0 0 0