A Digits-Recognition Convolutional Neural Network on FPGA
A convolutional neural network (CNN) is a deep learning framework that is widely used in computer vision. A CNN extracts important features of input images by perform- ing convolution and reduces the parameters in the network by applying pooling operation. CNNs are usually implemented with programmi...
Main Author: | |
---|---|
Format: | Others |
Language: | English |
Published: |
Linköpings universitet, Datorteknik
2019
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-161663 |
id |
ndltd-UPSALLA1-oai-DiVA.org-liu-161663 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-UPSALLA1-oai-DiVA.org-liu-1616632019-11-06T04:25:49ZA Digits-Recognition Convolutional Neural Network on FPGAengEtt faltningsbaserat neuralt nätverk för sifferigenkänning på FPGAWang, ZhenyuLinköpings universitet, Datorteknik2019Embedded SystemsInbäddad systemteknikA convolutional neural network (CNN) is a deep learning framework that is widely used in computer vision. A CNN extracts important features of input images by perform- ing convolution and reduces the parameters in the network by applying pooling operation. CNNs are usually implemented with programming languages and run on central process- ing units (CPUs) and graphics processing units (GPUs). However in recent years, research has been conducted to implement CNNs on field-programmable gate array (FPGA). The objective of this thesis is to implement a CNN on an FPGA with few hardware resources and low power consumption. The CNN we implement is for digits recognition. The input of this CNN is an image of a single digit. The CNN makes inference on what number it is on that image. The performance and power consumption of the FPGA is compared with that of a CPU and a GPU. The results show that our FPGA implementation has better performance than the CPU and the GPU, with respect to runtime, power consumption, and power efficiency. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-161663application/pdfinfo:eu-repo/semantics/openAccess |
collection |
NDLTD |
language |
English |
format |
Others
|
sources |
NDLTD |
topic |
Embedded Systems Inbäddad systemteknik |
spellingShingle |
Embedded Systems Inbäddad systemteknik Wang, Zhenyu A Digits-Recognition Convolutional Neural Network on FPGA |
description |
A convolutional neural network (CNN) is a deep learning framework that is widely used in computer vision. A CNN extracts important features of input images by perform- ing convolution and reduces the parameters in the network by applying pooling operation. CNNs are usually implemented with programming languages and run on central process- ing units (CPUs) and graphics processing units (GPUs). However in recent years, research has been conducted to implement CNNs on field-programmable gate array (FPGA). The objective of this thesis is to implement a CNN on an FPGA with few hardware resources and low power consumption. The CNN we implement is for digits recognition. The input of this CNN is an image of a single digit. The CNN makes inference on what number it is on that image. The performance and power consumption of the FPGA is compared with that of a CPU and a GPU. The results show that our FPGA implementation has better performance than the CPU and the GPU, with respect to runtime, power consumption, and power efficiency. |
author |
Wang, Zhenyu |
author_facet |
Wang, Zhenyu |
author_sort |
Wang, Zhenyu |
title |
A Digits-Recognition Convolutional Neural Network on FPGA |
title_short |
A Digits-Recognition Convolutional Neural Network on FPGA |
title_full |
A Digits-Recognition Convolutional Neural Network on FPGA |
title_fullStr |
A Digits-Recognition Convolutional Neural Network on FPGA |
title_full_unstemmed |
A Digits-Recognition Convolutional Neural Network on FPGA |
title_sort |
digits-recognition convolutional neural network on fpga |
publisher |
Linköpings universitet, Datorteknik |
publishDate |
2019 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-161663 |
work_keys_str_mv |
AT wangzhenyu adigitsrecognitionconvolutionalneuralnetworkonfpga AT wangzhenyu ettfaltningsbaseratneuraltnatverkforsifferigenkanningpafpga AT wangzhenyu digitsrecognitionconvolutionalneuralnetworkonfpga |
_version_ |
1719287513006211072 |