tensorflow-tf.nn.conv2d卷积运算(1)

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

@author: myhaspl
@email:[email protected]
tf.nn.conv2d
"""

import tensorflow as tf

g=tf.Graph()

with g.as_default():
    x=tf.constant([
            [[[3.]]
            ]])
    kernel=tf.constant([[[[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 x.get_shape()
    print kernel.get_shape()

    print sess.run(y)

[[[[3.]]]]
[[[[2.]]]]
(1, 1, 1, 1)
(1, 1, 1, 1)
[[[[6.]]]]

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

@author: myhaspl
@email:[email protected]
"""

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([[[[2.]]]])
    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 sess.run(y)

(2, 3, 2, 1)
[[[[  2.]
   [  4.]]

  [[  6.]
   [  8.]]

  [[ 10.]
   [ 12.]]]

 [[[ 20.]
   [ 40.]]

  [[ 60.]
   [ 80.]]

  [[100.]
   [120.]]]]

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

@author: myhaspl
@email:[email protected]
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([[[[2.,3.]]]])
    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 x.get_shape()
    print sess.run(y)

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

  [[ 3.]
   [ 4.]]

  [[ 5.]
   [ 6.]]]

 [[[10.]
   [20.]]

  [[30.]
   [40.]]

  [[50.]
   [60.]]]]
(2, 3, 2, 1)
[[[[  2.   3.]
   [  4.   6.]]

  [[  6.   9.]
   [  8.  12.]]

  [[ 10.  15.]
   [ 12.  18.]]]

 [[[ 20.  30.]
   [ 40.  60.]]

  [[ 60.  90.]
   [ 80. 120.]]

  [[100. 150.]
   [120. 180.]]]]