tensorflow-tf.nn.conv2d卷积运算(2)

tf.nn.conv2d(
input,
filter,
strides,
padding,
use_cudnn_on_gpu=True,
data_format='NHWC',
dilations=[1, 1, 1, 1],
name=None
)

计算给定4d输入和过滤核张量的二维卷积。

给定形状[batch，in_height, in_width, in_channels]的输入张量和形状[filter_height, filter_width, in_channels, out_channels]的筛选/核张量，此op执行如下操作:
将过滤核压扁到一个二维矩阵，形状为[filter_height filter_width in_channels, output_channels]。
从输入张量中提取图像块，形成一个形状的虚拟张量[batch, out_height, out_width, filter_height filter_width in_channels]。
对于每个patch，右乘滤波器矩阵和图像patch向量。

output[b, i, j, k] =
sum_{di, dj, q} input[b, strides[1] * i + di, strides[2] * j + dj, q] *
filter[di, dj, q, k]

必须有strides(步长)[0]=strides[3]= 1。对于相同水平和顶点的最常见情况，stride = [1, stride, stride, 1]。

Args:
input:一个张量。必须是以下类型之一:half，bfloat16, float32, float64。一个四维张量。dimension顺序是根据data_format的值来解释的。
filter: 必须具有与输入相同的类型。形状的4维张量[filter_height, filter_width, in_channels, out_channels]。
strides: int型列表。长度为4的一维张量。每个输入维度的滑动窗口的跨步。顺序是根据data_format的值来解释的。
padding: 来自:“SAME”、“VALID”的字符串。要使用的填充算法的类型。

use_cudnn_on_gpu: 可选bool,默认为True.
data_format: 一个可选的字符串:“NHWC”、“NCHW”。默认为“NHWC”。指定输入和输出数据的数据格式。使用默认格式“NHWC”，数据按以下顺序存储:[批处理、高度、宽度、通道]。或者，格式可以是“NCHW”，数据存储顺序为:[批处理，通道，高度，宽度]。
dilations:int的可选列表。默认为[1,1,1,1]。长度为4的一维张量。每个输入维度的膨胀系数。如果设置为k > 1，则该维度上的每个过滤器元素之间将有k-1跳过单元格。维度顺序由data_format的值决定，详细信息请参阅上面的内容。批次的膨胀和深度尺寸必须为1。
name: 可选 名字

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Tue Oct  2 13:23:27 2018

@author: myhaspl
@email:myhaspl@myhaspl.com
tf.nn.conv2d
"""

import tensorflow as tf

g=tf.Graph()

with g.as_default():
x=tf.constant([[
[[1.,2.],[3.,4.],[5.,6.]],
[[10.,20.],[30.,40.],[50.,60.]],
]])
kernel=tf.constant([[[[10.],[2.]]]])
y=tf.nn.conv2d(x,kernel,strides=[1,1,1,1],padding="SAME")

with tf.Session(graph=g) as sess:
print sess.run(x)
print sess.run(kernel)
print kernel.get_shape()
print x.get_shape()
print sess.run(y)

[[[[ 1.  2.]
[ 3.  4.]
[ 5.  6.]]

[[10. 20.]
[30. 40.]
[50. 60.]]]]
[[[[10.]
[ 2.]]]]
(1, 1, 2, 1)
(1, 2, 3, 2)
[[[[ 14.]
[ 38.]

3344
[ 62.]]

[[140.]
[380.]
[620.]]]]

import tensorflow as tf

a = tf.constant([1,1,1,0,0,0,1,1,1,0,0,0,1,1,1,0,0,1,1,0,0,1,1,0,0],dtype=tf.float32,shape=[1,5,5,1])
b = tf.constant([1,0,1,0,1,0,1,0,1],dtype=tf.float32,shape=[3,3,1,1])
c = tf.nn.conv2d(a,b,strides=[1, 2, 2, 1],padding='VALID')
d = tf.nn.conv2d(a,b,strides=[1, 2, 2, 1],padding='SAME')
with tf.Session() as sess:
print ("c shape:")
print (c.shape)
print ("c value:")
print (sess.run(c))
print ("d shape:")
print (d.shape)
print ("d value:")
print (sess.run(d))

conv2d(
input,
filter,
strides,
padding,
use_cudnn_on_gpu=True,
data_format='NHWC',
name=None
)

c shape:
(1, 2, 2, 1)
c value:
[[[[ 4.]
[ 4.]]

[[ 2.]
[ 4.]]]]
d shape:
(1, 3, 3, 1)
d value:
[[[[ 2.]
[ 3.]
[ 1.]]

[[ 1.]
[ 4.]
[ 3.]]

[[ 0.]
[ 2.]
[ 1.]]]]

padding为VALID，采用丢弃的方式。

padding为SAME,采用的是补全的方式,补0

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Tue Oct  2 13:23:27 2018

@author: myhaspl
@email:myhaspl@myhaspl.com
tf.nn.conv2d
"""

import tensorflow as tf

g=tf.Graph()

with g.as_default():
x=tf.constant([
[
[[1.],[2.],[11.]],
[[3.],[4.],[22.]],
[[5.],[6.],[33.]]
],
[
[[10.],[20.],[44.]],
[[30.],[40.],[55.]],
[[50.],[60.],[66.]]
]
])#2*3*3*1
kernel=tf.constant(
[
[[[2.]],[[3.]]]
]
)#2*2*1
y=tf.nn.conv2d(x,kernel,strides=[1,1,1,1],padding="SAME")

with tf.Session(graph=g) as sess:
print x.get_shape()
print kernel.get_shape()
print sess.run(y)
print y.get_shape()

padding="SAME"
$12+23=8$
$22+311=37$
$112+03=22$

(2, 3, 3, 1)
(1, 2, 1, 1)
[[[[  8.]
[ 37.]
[ 22.]]

[[ 18.]
[ 74.]
[ 44.]]

[[ 28.]
[111.]
[ 66.]]]

[[[ 80.]
[172.]
[ 88.]]

[[180.]
[245.]
[110.]]

[[280.]
[318.]
[132.]]]]
(2, 3, 3, 1)