tf.nn.conv2d()函数
参数介绍:
tf.nn.conv2d(input, filter, strides, padding, use_cudnn_on_gpu=None, name=None)
input:输入参数,具有这样的shape[batch, in_height, in_width, in_channels],分别是[batch张图片, 每张图片高度为in_height, 每张图片宽度为in_width, 图像通道为in_channels].
filter:滤波器,滤波器的shape为[filter_height, filter_width, in_channels, out_channels],分别对应[滤波器高度, 滤波器宽度, 接受图像的通道数, 卷积后通道数],其中第三个参数 in_channels需要与input中的第四个参数 in_channels一致.
strides:代表步长,其值可以直接默认一个数,也可以是一个四维数如[1,2,1,1],则其意思是水平方向卷积步长为第二个参数2,垂直方向步长为1.
padding:代表填充方式,参数只有两种,SAME和VALID,SAME比VALID的填充方式多了一列,比如一个3*3图像用2*2的滤波器进行卷积,当步长设为2的时候,会缺少一列,则进行第二次卷积的时候,VALID发现余下的窗口不足2*2会直接把第三列去掉,SAME则会填充一列,填充值为0.
use_cudnn_on_gpu:bool类型,是否使用cudnn加速,默认为true.
name:给返回的tensor命名。给输出feature map起名字.
例子:
一张3*3的图片,元素如下:
* | * | * |
---|---|---|
0 | 3 | 6 |
1 | 4 | 7 |
2 | 5 | 8 |
卷积核为1个2*2的卷积,如下:
* | * |
---|---|
0 | 2 |
1 | 3 |
TensorFlow代码(padding为SAME):
import tensorflow as tf
import numpy as np
g = tf.Graph()
with g.as_default() as g:
input = tf.Variable(np.array(range(9), dtype=np.float32).reshape(1,3,3,1))
filter = tf.Variable(np.array(range(4), dtype=np.float32).reshape(2,2,1,1))
op = tf.nn.conv2d(input, filter, strides=[1, 1, 1, 1], padding=‘SAME‘)
with tf.Session(graph=g) as sess:
sess.run(tf.global_variables_initializer())
a,b,c = sess.run([input, filter, op])
print(a)
print(b)
print(c)
输出:
[[[[ 0.]
[ 1.]
[ 2.]]
[[ 3.]
[ 4.]
[ 5.]]
[[ 6.]
[ 7.]
[ 8.]]]]
[[[[ 0.]]
[[ 1.]]]
[[[ 2.]]
[[ 3.]]]]
[[[[ 19.]
[ 25.]
[ 10.]]
[[ 37.]
[ 43.]
[ 16.]]
[[ 7.]
[ 8.]
[ 0.]]]]
即卷积后的结果为:
* | * | * |
---|---|---|
19 | 37 | 7 |
25 | 43 | 8 |
10 | 16 | 0 |
如果padding为VALID,则输出如下:
[[[[ 0.]
[ 1.]
[ 2.]]
[[ 3.]
[ 4.]
[ 5.]]
[[ 6.]
[ 7.]
[ 8.]]]]
[[[[ 0.]]
[[ 1.]]]
[[[ 2.]]
[[ 3.]]]]
[[[[ 19.]
[ 25.]]
[[ 37.]
[ 43.]]]]
即卷积后的结果为:
* | * |
---|---|
19 | 37 |
25 | 43 |
tf.nn.max_pool()函数
tf.nn.max_pool(value, ksize, strides, padding, name=None)
参数是四个,和卷积函数很类似:
value:需要池化的输入,一般池化层接在卷积层后面,所以输入通常是feature map,依然是[batch, height, width, channels]这样的shape.
ksize:池化窗口的大小,取一个四维向量,一般是[1, height, width, 1],因为我们不想在batch和channels上做池化,所以这两个维度设为了1.
strides:和卷积类似,窗口在每一个维度上滑动的步长,一般也是[1, stride,stride, 1].
padding:和卷积类似,可以取‘VALID‘ 或者‘SAME‘.
返回一个Tensor,类型不变,shape仍然是[batch, height, width, channels]这种形式.
TensorFlow代码:
import tensorflow as tf
import numpy as np
g = tf.Graph()
with g.as_default() as g:
input = tf.Variable(np.array(range(9), dtype=np.float32).reshape(1,3,3,1))
filter = tf.Variable(np.array(range(4), dtype=np.float32).reshape(2,2,1,1))
op = tf.nn.conv2d(input, filter, strides=[1, 1, 1, 1], padding=‘SAME‘)
pool = tf.nn.max_pool(op, [1,2,2,1], [1,1,1,1], padding=‘SAME‘)
with tf.Session(graph=g) as sess:
sess.run(tf.global_variables_initializer())
PL = sess.run(pool)
print(PL)
输出:
[[[[ 43.]
[ 43.]
[ 16.]]
[[ 43.]
[ 43.]
[ 16.]]
[[ 8.]
[ 8.]
[ 0.]]]]
* | * | * |
---|---|---|
43 | 43 | 8 |
43 | 43 | 8 |
16 | 16 | 0 |
tf.nn.avg_pool()
计算方法: 计算非padding的元素的平均值
例子:
import tensorflow as tf
import numpy as np
g = tf.Graph()
with g.as_default() as g:
input = tf.Variable(np.array(range(9), dtype=np.float32).reshape(1,3,3,1))
filter = tf.Variable(np.array(range(4), dtype=np.float32).reshape(2,2,1,1))
op = tf.nn.conv2d(input, filter, strides=[1, 1, 1, 1], padding=‘SAME‘)
pool = tf.nn.avg_pool(op, [1,2,2,1], [1,1,1,1], padding=‘SAME‘)
with tf.Session(graph=g) as sess:
sess.run(tf.global_variables_initializer())
PL = sess.run(pool)
print(PL)
输出为:
[[[[31. ]
[23.5 ]
[13. ]]
[[23.75]
[16.75]
[ 8. ]]
[[ 7.5 ]
[ 4. ]
[ 0. ]]]]
* | * | * |
---|---|---|
31 | 23.75 | 7.5 |
23.5 | 16.75 | 4. |
13. | 8. | 0. |
tf.nn.dropout()
tf.nn.dropout(x, keep_prob, noise_shape=None, seed=None, name=None)
tensorflow中的dropout就是:shape不变,使输入tensor中某些元素按照一定的概率变为0,其它没变0的元素变为原来的1/keep_prob.
dropout层的作用: 防止神经网络的过拟合
例子:
import tensorflow as tf
g = tf.Graph()
with g.as_default() as g:
mat = tf.Variable(tf.ones([10,10]))
dropout_mat = tf.nn.dropout(mat, keep_prob=0.5)
with tf.Session(graph=g) as sess:
sess.run(tf.global_variables_initializer())
output, dropout = sess.run([mat, dropout_mat])
print(output)
print(dropout)
输出:
[[1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]]
[[2. 0. 0. 0. 2. 0. 2. 2. 0. 2.]
[0. 2. 0. 0. 2. 2. 0. 0. 0. 0.]
[2. 2. 2. 0. 0. 2. 0. 2. 0. 0.]
[2. 0. 0. 0. 2. 2. 2. 0. 2. 0.]
[0. 2. 2. 0. 2. 2. 2. 2. 0. 2.]
[2. 0. 0. 0. 2. 0. 0. 2. 0. 2.]
[2. 2. 0. 2. 2. 0. 0. 0. 2. 2.]
[2. 0. 0. 0. 0. 2. 0. 2. 0. 0.]
[2. 2. 0. 0. 0. 0. 0. 2. 0. 0.]
[2. 0. 2. 2. 2. 2. 0. 2. 0. 0.]]
tf.reshape()
shape里最多有一个维度的值可以填写为-1,表示自动计算此维度
原文:https://www.cnblogs.com/jclian91/p/9520233.html