Skip to Content
深度学习入门 : 基于Python的理论与实现
book

深度学习入门 : 基于Python的理论与实现

by 斋藤康毅
July 2018
Intermediate to advanced
310 pages
8h 21m
Chinese
Posts & Telecom Press
Content preview from 深度学习入门 : 基于Python的理论与实现
7.2  卷积层 
203
7.2.1
 全连接层存在的问题
之前介绍的全连接的神经网络中使用了全连接层(
Affine
层)。在全连接
层中,相邻层的神经元全部连接在一起,输出的数量可以任意决定。
全连接层存在什么问题呢?那就是数据的形状被“忽视”了。比如,输
入数据是图像时,图像通常是高、长、通道方向上的3 维形状。但是,向全
连接层输入时,需要将 3 维数据拉平为1 维数据。实际上,前面提到的使用
MNIST
数据集的例子中,输入图像就是1 通道、高 28 像素、长 28 像素
的(1, 28, 28)形状,但却被排成1 列,以 784 个数据的形式输入到最开始的
Affine
层。
图像是3 维形状,这个形状中应该含有重要的空间信息。比如,空间上
邻近的像素为相似的值、
RBG
的各个通道之间分别有密切的关联性、相距
较远的像素之间没有什么关联等,3 维形状中可能隐藏有值得提取的本质模
式。但是,因为全连接层会忽视形状,将全部的输入数据作为相同的神经元
(同一维度的神经元)处理,所以无法利用与形状相关的信息。
而卷积层可以保持形状不变。当输入数据是图像时,卷积层会以3
数据的形式接收输入数据,并同样以3 维数据的形式输出至下一层。因此,
CNN
中,可以(有可能)正确理解图像等具有形状的数据。
另外,
CNN
中,有时将卷积层的输入输出数据称为特征图
feature
map
)。其中,卷积层的输入数据称为输入特征图
input feature map
),
数据称为输出特征图
output feature map
)。本书中将 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

AirBnbBlueOriginElectronic ArtsHomeDepotNasdaqRakutenTata Consultancy Services

QuotationMarkO’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
Julian F.
Head of Cybersecurity
QuotationMarkI wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.
Addison B.
Field Engineer
QuotationMarkI’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.
Amir M.
Data Platform Tech Lead
QuotationMarkI'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Mark W.
Embedded Software Engineer

You might also like

ルールズ・オブ・プログラミング ―より良いコードを書くための21のルール

ルールズ・オブ・プログラミング ―より良いコードを書くための21のルール

Chris Zimmerman, 久富木 隆一

Publisher Resources

ISBN: 9787115485588