CNN初步-2
Pooling
为了解决convolved之后输出维度太大的问题
在convolved的特征基础上采用的不是相交的区域处理
http://www.wildml.com/2015/11/understanding-convolutional-neural-networks-for-nlp/
这里有一个cnn较好的介绍
Pooling also reduces the output dimensionality but (hopefully) keeps the most salient information.
By performing the max operation you are keeping information about whether or not the feature appeared in the sentence, but you are losing information about where exactly it appeared.
You are losing global information about locality (where in a sentence something happens), but you are keeping local information captured by your filters, like "not amazing" being very different from "amazing not".
局部信息能够学到 "not amaziing" "amzaing not"这样 bag of word 不行的顺序信息(知道他们是不一样的),然后max pooling仍然能够保留这一信息
只是丢失了这个信息的具体位置
There are two aspects of this computation worth paying attention to: Location Invarianceand Compositionality. Let's say you want to classify whether or not there's an elephant in an image. Because you are sliding your filters over the whole
image you don't really care wherethe elephant occurs. In practice, pooling also gives you invariance to translation, rotation and scaling, but more on that later. The second key aspect is (local) compositionality. Each filter composes a local patch of lower-level features into higher-level representation. That's why CNNs are so powerful in Computer Vision. It makes intuitive sense that you build edges from pixels, shapes from edges, and more complex objects from shapes.
来自 <http://www.wildml.com/2015/11/understanding-convolutional-neural-networks-for-nlp/>
关于conv和pooling可选的参数
PADDING
You can see how wide convolution is useful, or even necessary, when you have a large filter relative to the input size. In the above, the narrow convolution yields an output of size
, and a wide convolution an output of size
. More generally, the formula for the output size is
.
来自 <http://www.wildml.com/2015/11/understanding-convolutional-neural-networks-for-nlp/>
narrow对应 tensorflow提供的VALID padding
wide对应tensorflow提供其中特定一种 SAME padding(zero padding)通过补齐0 来保持输出不变
下面有详细解释
STRIDE
这个比较好理解
每次移动的距离,对应pooling, filter size是多少
一般 stride是多少
down vote
|
tensorflow里面提供SAME,VALID两种padding的选择 关于padding, conv和pool用的padding都是同一个padding算法 The TensorFlow Convolution example gives an overview about the difference between SAME and VALID :
And
|
示例
In [2]:
import
tensorflow
as
tf
x = tf.constant([[1., 2., 3.],
[4., 5., 6.]])
x = tf.reshape(x, [1, 2, 3, 1]) # give a shape accepted by tf.nn.max_pool
valid_pad = tf.nn.max_pool(x, [1, 2, 2, 1], [1, 2, 2, 1], padding='VALID')
same_pad = tf.nn.max_pool(x, [1, 2, 2, 1], [1, 2, 2, 1], padding='SAME')
print valid_pad.get_shape() == [1, 1, 1, 1] # valid_pad is [5.]
print same_pad.get_shape() == [1, 1, 2, 1] # same_pad is [5., 6.]
sess = tf.InteractiveSession()
sess.run(tf.initialize_all_variables())
print valid_pad.eval()
print same_pad.eval()
True
True
[[[[ 5.]]]]
[[[[ 5.]
[ 6.]]]]
In [7]:
x = tf.constant([[1., 2., 3., 4.],
[4., 5., 6., 7.],
[8., 9., 10., 11.],
[12.,13.,14.,15.]])
x = tf.reshape(x, [1, 4, 4, 1]) # give a shape accepted by tf.nn.max_pool
valid_pad = tf.nn.max_pool(x, [1, 2, 2, 1], [1, 2, 2, 1], padding='VALID')
same_pad = tf.nn.max_pool(x, [1, 2, 2, 1], [1, 2, 2, 1], padding='SAME')
print valid_pad.get_shape() # valid_pad is [5.]
print same_pad.get_shape() # same_pad is [5., 6.]
#ess = tf.InteractiveSession()
#ess.run(tf.initialize_all_variables())
print valid_pad.eval()
print same_pad.eval()
(1, 2, 2, 1)
(1, 2, 2, 1)
[[[[ 5.]
[ 7.]]
[[ 13.]
[ 15.]]]]
[[[[ 5.]
[ 7.]]
[[ 13.]
[ 15.]]]]
In [8]:
x = tf.constant([[1., 2., 3., 4.],
[4., 5., 6., 7.],
[8., 9., 10., 11.],
[12.,13.,14.,15.]])
x = tf.reshape(x, [1, 4, 4, 1]) # give a shape accepted by tf.nn.max_pool
W = tf.constant([[1., 0.],
[0., 1.]])
W = tf.reshape(W, [2, 2, 1, 1])
valid_pad = tf.nn.conv2d(x, W, strides = [1, 1, 1, 1], padding='VALID')
same_pad = tf.nn.conv2d(x, W, strides = [1, 1, 1, 1],padding='SAME')
print valid_pad.get_shape()
print same_pad.get_shape()
#ess = tf.InteractiveSession()
#ess.run(tf.initialize_all_variables())
print valid_pad.eval()
print same_pad.eval()
(1, 3, 3, 1)
(1, 4, 4, 1)
[[[[ 6.]
[ 8.]
[ 10.]]
[[ 13.]
[ 15.]
[ 17.]]
[[ 21.]
[ 23.]
[ 25.]]]]
[[[[ 6.]
[ 8.]
[ 10.]
[ 4.]]
[[ 13.]
[ 15.]
[ 17.]
[ 7.]]
[[ 21.]
[ 23.]
[ 25.]
[ 11.]]
[[ 12.]
[ 13.]
[ 14.]
[ 15.]]]]
In [9]:
x = tf.constant([[1., 2., 3.],
[4., 5., 6.]])
x = tf.reshape(x, [1, 2, 3, 1]) # give a shape accepted by tf.nn.max_pool
W = tf.constant([[1., 0.],
[0., 1.]])
W = tf.reshape(W, [2, 2, 1, 1])
valid_pad = tf.nn.conv2d(x, W, strides = [1, 1, 1, 1], padding='VALID')
same_pad = tf.nn.conv2d(x, W, strides = [1, 1, 1, 1],padding='SAME')
print valid_pad.get_shape()
print same_pad.get_shape()
#ess = tf.InteractiveSession()
#ess.run(tf.initialize_all_variables())
print valid_pad.eval()
print same_pad.eval()
(1, 1, 2, 1)
(1, 2, 3, 1)
[[[[ 6.]
[ 8.]]]]
[[[[ 6.]
[ 8.]
[ 3.]]
[[ 4.]
[ 5.]
[ 6.]]]]
In [ ]:
CNN初步-2的更多相关文章
- CNN初步-1
Convolution: 个特征,则这时候把输入层的所有点都与隐含层节点连接,则需要学习10^6个参数,这样的话在使用BP算法时速度就明显慢了很多. 所以后面就发展到了局部连接网络,也就是说每个隐 ...
- 初步认识CNN
1.机器学习 (1)监督学习:有数据和标签 (2)非监督学习:只有数据,没有标签 (3)半监督学习:监督学习+非监督学习 (4)强化学习:从经验中总结提升 (5)遗传算法:适者生存,不适者淘汰 2.神 ...
- 卷积神经网络(CNN)学习算法之----基于LeNet网络的中文验证码识别
由于公司需要进行了中文验证码的图片识别开发,最近一段时间刚忙完上线,好不容易闲下来就继上篇<基于Windows10 x64+visual Studio2013+Python2.7.12环境下的C ...
- (六)6.18 cnn 的反向传导算法
本文主要内容是 CNN 的 BP 算法,看此文章前请保证对CNN有初步认识,可参考Neurons Networks convolutional neural network(cnn). 网络表示 CN ...
- [置顶] VB6基本数据库应用(三):连接数据库与SQL语句的Select语句初步
同系列的第三篇,上一篇在:http://blog.csdn.net/jiluoxingren/article/details/9455721 连接数据库与SQL语句的Select语句初步 ”前文再续, ...
- Tensorflow的CNN教程解析
之前的博客我们已经对RNN模型有了个粗略的了解.作为一个时序性模型,RNN的强大不需要我在这里重复了.今天,让我们来看看除了RNN外另一个特殊的,同时也是广为人知的强大的神经网络模型,即CNN模型.今 ...
- 用于NLP的CNN架构搬运:from keras0.x to keras2.x
本文亮点: 将用于自然语言处理的CNN架构,从keras0.3.3搬运到了keras2.x,强行练习了Sequential+Model的混合使用,具体来说,是Model里嵌套了Sequential. ...
- 深入学习卷积神经网络(CNN)的原理知识
网上关于卷积神经网络的相关知识以及数不胜数,所以本文在学习了前人的博客和知乎,在别人博客的基础上整理的知识点,便于自己理解,以后复习也可以常看看,但是如果侵犯到哪位大神的权利,请联系小编,谢谢.好了下 ...
- CS229 6.18 CNN 的反向传导算法
本文主要内容是 CNN 的 BP 算法,看此文章前请保证对CNN有初步认识. 网络表示 CNN相对于传统的全连接DNN来说增加了卷积层与池化层,典型的卷积神经网络中(比如LeNet-5 ),开始几层都 ...
随机推荐
- zapewnia stale poprawiając relacje związane
W porównaniu do LG5, ta http://www.butyrunning.com/lunarestoa-2-m%C3%84%C2%99skie-c-2_70_71.html kon ...
- Windows 下安装 MongoDB
Windows 下安装 MongoDB 的步骤:1.官网www.mongodb.com下载安装包或zip包2.解压下载的文件到文件夹 D:\mongo .3.使用管理员权限打开CMD,导航到目录 D: ...
- 【Redis安装学习】
1.Redis 中文官网地址:http://www.redis.net.cn/download/ 这里只是简单的安装了下.具体的官网有详细的介绍和安装:跳转 如何安装 下载,解压,编译: $ wget ...
- SQL Server 2008在Windows 10上不支持
https://support.microsoft.com/en-us/kb/2681562 For SQL Server 2008 R2 SQL Server 2008 R2 is not supp ...
- Unity3D Editor 扩展
官方教程:链接 EditorLayout API:链接 Handles API:链接 1.首先来个Inspector面板Editor的实现 要实现一个组件在Inspector中的Editor功能,首先 ...
- unixLike命令拾遗
针对在日常工作过程中,发现的学习的漏洞和忘记的知识,进行拾遗. 编辑命令 一.vim操作 1.进入编辑模式 在光标移到将要编辑处,点击i,进入编辑模式 2.退出编辑模式 按esc或者crtl+c退出编 ...
- php打印中文乱码
php文档的文本格式都设置成 utf-8 格式 在代码中添加 header("content-type:text/html; charset=utf-8");
- iOS中RSA加密详解
先贴出代码的地址,做个说明,因为RSA加密在iOS的代码比较少,网上开源的也很少,最多的才8个星星.使用过程中发现有错误.然后我做了修正,和另一个库进行了整合,然后将其支持CocoaPod. http ...
- .net导入excel数据到数据库中
在开发过程中我们经常面临着需要将数据导出或者导入到系统中,例如一些生产管理系统,项目管理系统等等都会有这样的需求: 将excel数据到系统中思路:获取excel中每一行的数据,然后存入集合中,批量添加 ...
- 请不要重复犯我在学习Python和Linux系统上的错误
本人已经在运维行业工作了将近十年,我最早接触Linux是在大二的样子,那时候只追求易懂,所以就选择了Ubuntu作为学习.使用的对象,它简单.易用.好操作.界面绚丽,对于想接触Linux的新手来说是非 ...