Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Acceleration of deep convolutional neural networks on multiprocessor system-on-chip
Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för datorteknik.
2019 (Engelska)Självständigt arbete på avancerad nivå (yrkesexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
Abstract [en]

In this master thesis some of the most promising existing frameworks and implementations of deep convolutional neural networks on multiprocessor system-on-chips (MPSoCs) are researched and evaluated. The thesis’ starting point was a previousthesis which evaluated possible deep learning models and frameworks for object detection on infra-red images conducted in the spring of 2018. In order to fit an existing deep convolutional neural network (DCNN) on a Multiple-Processor-System on Chip it needs modifications. Most DCNNs are trained on Graphic processing units (GPUs) with a bit width of 32 bit. This is not optimal for a platform with hard memory constraints such as the MPSoC which means it needs to be shortened. The optimal bit width depends on the network structure and requirements in terms of throughput and accuracy although most of the currently available object detection networks drop significantly when reduced below 6 bits width. After reducing the bit width, the network needs to be quantized and pruned for better memory usage. After quantization it can be implemented using one of many existing frameworks. This thesis focuses on Xilinx CHaiDNN and DNNWeaver V2 though it touches a little on revision, HLS4ML and DNNWeaver V1 as well. In conclusion the implementation of two network models on Xilinx Zynq UltraScale+ ZCU102 using CHaiDNN were evaluated. Conversion of existing network were done and quantization tested though not fully working. The results were a two to six times more power efficient implementation in comparison to GPU inference.

Ort, förlag, år, upplaga, sidor
2019. , s. 48
Serie
UPTEC E, ISSN 1654-7616 ; 19006
Nyckelord [sv]
Neurala nätverk, MPSoC, FPGA, DCNN
Nationell ämneskategori
Inbäddad systemteknik
Identifikatorer
URN: urn:nbn:se:uu:diva-385904OAI: oai:DiVA.org:uu-385904DiVA, id: diva2:1326323
Utbildningsprogram
Civilingenjörsprogrammet i elektroteknik
Presentation
2019-06-10, 2003, Lägerhyddsvägen 1, Uppsala, 08:06 (Engelska)
Handledare
Examinatorer
Tillgänglig från: 2019-06-26 Skapad: 2019-06-18 Senast uppdaterad: 2019-06-26Bibliografiskt granskad

Open Access i DiVA

Acceleration of deep convolutional neural networks on multiprocessor system-on-chip(6529 kB)231 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 6529 kBChecksumma SHA-512
72e06d3235d45132292efba0110c94c950188919105b6fd700b19317fabe0e41ca9afd983c06ec7d22cc1e2a69d8168a87f54f8e0c8ab850213fc328f3e4baa6
Typ fulltextMimetyp application/pdf

Av organisationen
Avdelningen för datorteknik
Inbäddad systemteknik

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 231 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 305 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf