July 2018
Intermediate to advanced
310 pages
8h 21m
Chinese
Content preview from 深度学习入门 : 基于Python的理论与实现
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,
O’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.I 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.I’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.I'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.
7.2 卷积层
213
图7-12 卷积运算的处理流（追加了偏置项）
+
+
H
FH
FN个
FW
W
OH
1
1
OW
(C, H, W) (FN, C, FH, FW) (FN, OH, OW)
C
C
FN
FN
输入数据
(FN, OH, OW)
输出数据
(FN, 1, 1)
偏置滤波器
FN
FN
OH
OW
FN
FN
7.2.7
批处理
神经网络的处理中进行了将输入数据打包的批处理。之前的全连接神经
网络的实现也对应了批处理，通过批处理，能够实现处理的高效化和学习时
对
mini-batch
的对应。
我们希望卷积运算也同样对应批处理。为此，需要将在各层间传递的数
据保存为4 维数据。具体地讲，就是按
(batch
_
num
,
channel
,
height
,
width)
的顺序保存数据。比如，将图7
-
12 中的处理改成对
N
个数据进行批处理时，
数据的形状如图7
-
13 所示。
图 7
-
13 的批处理版的数据流中，在各个数据的开头添加了批用的维度。
像这样，数据作为4 维的形状在各层间传递。这里需要注意的是，网络间传
递的是4 维数据，对这
N
个数据进行了卷积运算。也就是说，批处理将
N
次
的处理汇总成了1 次进行。
图7-13 卷积运算的处理流（批处理）
*
+
+
*
H
N 个数据 N 个数据 N 个数据
FH
FN 个
FW
W
OH
1
1
OW
(N, C, H, W) (FN, C, FH, FW) (N, FN, OH, OW)
C
C
FN
FN
输入数据
(N, FN, OH, OW)
输出数据
(FN, 1, 1)
偏置滤波器
FN
FN
FN
OH
OW
FN
FN
FN
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
O’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.
I 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.
I’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.
I'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.