没有合适的资源?快使用搜索试试~ 我知道了~
首页ZynqNet: An FPGA-Accelerated Embedded Convolutional Neural Network
资源详情
资源评论
资源推荐
Master Thesis Report
ZynqNet:
An FPGA-Accelerated Embedded
Convolutional Neural Network
1000ch
1000ch
SqueezeNet v1.1 b2a ext7 conv10 2x416 >
2x512 > 1024 (edit)
Network Analysis
1000ch
SqueezeNet v1.1 b2a ext7 conv10 2x416 >
2x512 > 1024 (edit)
Network Analysis
FPGA
David Gschwend
davidgs@student.ethz.ch
Supervisors: Emanuel Schmid
Felix Eberli
Professor: Prof. Dr. Anton Gunzinger
August 2016, ETH Zürich,
Department of Information Technology and Electrical Engineering
Abstract
Image Understanding is becoming a vital feature in ever more applications ranging from
medical diagnostics to autonomous vehicles. Many applications demand for embedded
solutions that integrate into existing systems with tight real-time and power constraints.
Convolutional Neural Networks (CNNs) presently achieve record-breaking accuracies in
all image understanding benchmarks, but have a very high computational complexity.
Embedded CNNs thus call for small and efficient, yet very powerful computing platforms.
This master thesis explores the potential of FPGA-based CNN acceleration and demonstrates
a fully functional proof-of-concept CNN implementation on a Zynq System-on-Chip. The
ZynqNet Embedded CNN is designed for image classification on ImageNet and consists of
ZynqNet CNN, an optimized and customized CNN topology, and the ZynqNet FPGA Accelerator,
an FPGA-based architecture for its evaluation.
ZynqNet CNN is a highly efficient CNN topology. Detailed analysis and optimization of
prior topologies using the custom-designed Netscope CNN Analyzer have enabled a CNN
with
84.5 %
top-5 accuracy at a computational complexity of only
530
million multiply-
accumulate operations. The topology is highly regular and consists exclusively of convolu-
tional layers, ReLU nonlinearities and one global pooling layer. The CNN fits ideally onto the
FPGA accelerator.
The ZynqNet FPGA Accelerator allows an efficient evaluation of ZynqNet CNN. It accelerates
the full network based on a nested-loop algorithm which minimizes the number of arithmetic
operations and memory accesses. The FPGA accelerator has been synthesized using High-
Level Synthesis for the Xilinx Zynq XC-7Z045, and reaches a clock frequency of
200 MHz
with a device utilization of 80 % to 90 %.
Organization of this report
Chapter 1 gives an overview of the current opportunities and
challenges regarding image understanding in embedded systems. The following chap-
ter 2 introduces the central concepts of Convolutional Neural Networks (CNNs) and Field-
Programmable Gate Arrays (FPGAs), as well as a number of CNN topologies and CNN
accelerators from prior work. Chapter 3 dives deep into the analysis, training and opti-
mization of CNN architectures, and presents our customized ZynqNet CNN topology. Next,
chapter 4 shifts the focus onto the design and implementation of our FPGA-based architec-
ture for the evaluation of CNNs, the ZynqNet FPGA Accelerator, and reports lessons learned
from the application of High-Level Synthesis. Finally, chapter 5 presents the performance
results of the overall ZynqNet Embedded CNN system, before the conclusion in chapter 6 puts
these in a bigger perspective.
iii
Acknowledgement
First and foremost, I would like to thank my supervisor Emanuel Schmid for the pleasant
collaboration, the fruitful discussions, the helpful guidance and his excellent support during
the project. You offered me full confidence and freedom, yet were always there when
I needed feedback, a different point of view or new ideas. I also thank Felix Eberli for
arranging this project, for involving me in various interesting meetings and discussions, and
for his generous support.
Special thanks also go to professor Dr. Anton Gunzinger for giving me the chance to work
on a fascinating project of practical relevance, and to the whole staff at Supercomputing
Systems AG for the warm welcome and the pleasant stay.
Finally, I want to express my gratitude to my family, my friends and my fiancée. You’ve always
had my back, and I could not have made it here without your constant and unconditional
support. Thank you.
v
剩余101页未读,继续阅读
hyfine_
- 粉丝: 369
- 资源: 10
上传资源 快速赚钱
- 我的内容管理 收起
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
会员权益专享
最新资源
- zigbee-cluster-library-specification
- JSBSim Reference Manual
- c++校园超市商品信息管理系统课程设计说明书(含源代码) (2).pdf
- 建筑供配电系统相关课件.pptx
- 企业管理规章制度及管理模式.doc
- vb打开摄像头.doc
- 云计算-可信计算中认证协议改进方案.pdf
- [详细完整版]单片机编程4.ppt
- c语言常用算法.pdf
- c++经典程序代码大全.pdf
- 单片机数字时钟资料.doc
- 11项目管理前沿1.0.pptx
- 基于ssm的“魅力”繁峙宣传网站的设计与实现论文.doc
- 智慧交通综合解决方案.pptx
- 建筑防潮设计-PowerPointPresentati.pptx
- SPC统计过程控制程序.pptx
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0