Loughborough University
Browse

Automated compilation of deep learning neural networks for image processing

Download (2.1 MB)
thesis
posted on 2022-09-08, 11:19 authored by George Waldie

In recent years, machine learning has very much been a prominent talking point, and is considered by many to be the next big thing, comparable to, if not greater than the dot-com boom of the late 90s. Whilst machine learning and AI are general terms, an area that has seen significant growth both in research and industrial or commercial applications are neural networks, especially those known as deep neural networks, where the increases in processing power available through higher core count CPUs and mutliple high power GPUs have meant that networks can now be far bigger than when they were originally put forward.

This work looks at a subsection of this field, focusing on network inference instead of training, and being able to utilise trained networks on multiple platforms as easily as possible. Due to the high growth of the area, there are many specialist tools available to allow users to use neural networks on a wide range of hardware, however in order to test and develop on multiple platforms such as x86 and embedded or FPGA systems, you are required to use multiple tools, each separate from one another. This work aims to provide a single solution allowing a user to test trained networks on multiple platforms, knowing the code base originates from the same core and lowering some of the difficulties that embedded or FPGA platforms can throw up when it comes to developing for them.

The system created allows a user to target multiple different platforms, automatically generating code to be used on each, reducing the number of steps required before the network can be up and running on the chosen device. TinyYOLO was the main network used for testing, on multiple x86 platforms, and a Digilent Zedboard for freeRTOS, PetaLinux and FPGA testing.

History

School

  • Mechanical, Electrical and Manufacturing Engineering

Publisher

Loughborough University

Rights holder

© George Waldie

Publication date

2021

Notes

A Master's Thesis. Submitted in partial fulfilment of the requirements for the award of the degree of Master of Philosophy of Loughborough University.

Language

  • en

Supervisor(s)

Vincent Dwyer ; Vasilios Chouliaras

Qualification name

  • MPhil

Qualification level

  • Masters

This submission includes a signed certificate in addition to the thesis file(s)

  • I have submitted a signed certificate

Usage metrics

    Mechanical, Electrical and Manufacturing Engineering Theses

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC