tensorflow 笔记11：tf.nn.dropout（） 的使用

tf.nn.dropout：函数
官网说明：

tf.nn.dropout(
    x,
    keep_prob,
    noise_shape=None,
    seed=None,
    name=None
)
Defined in tensorflow/python/ops/nn_ops.py.

See the guides: Layers (contrib) > Higher level ops for building neural network layers, Neural Network > Activation Functions

Computes dropout.

With probability keep_prob, outputs the input element scaled up by 1 / keep_prob, otherwise outputs 0. The scaling is so that the expected sum is unchanged.

By default, each element is kept or dropped independently. If noise_shape is specified, 
it must be broadcastable to the shape of x, and only dimensions with noise_shape[i] == shape(x)[i] will make independent decisions. For example, 

if shape(x) = [k, l, m, n] and noise_shape = [k, 1, 1, n], each batch and channel component will be kept independently and each row and column will be kept or not kept together.

Args:
x: A floating point tensor.
keep_prob: A scalar Tensor with the same type as x. The probability that each element is kept.
noise_shape: A 1-D Tensor of type int32, representing the shape for randomly generated keep/drop flags.
seed: A Python integer. Used to create random seeds. See tf.set_random_seed for behavior.
name: A name for this operation (optional).
Returns:
A Tensor of the same shape of x.

Raises:
ValueError: If keep_prob is not in (0, 1] or if x is not a floating point tensor.

使用说明：

参数 keep_prob: 表示的是保留的比例，假设为0.8 则 20% 的数据变为0，然后其他的数据乘以 1/keep_prob；keep_prob 越大，保留的越多；

参数 noise_shape：干扰形状。    此字段默认是None，表示第一个元素的操作都是独立，但是也不一定。比例：数据的形状是shape(x)=[k, l, m, n]，而noise_shape=[k, 1, 1, n]，则第1和4列是独立保留或删除，第2和3列是要么全部保留，要么全部删除。

代码举例：

import os
import numpy as np
import tensorflow as tf

x = tf.Variable(tf.ones([10, 10]))

inputs = tf.nn.dropout(x, 0.8)

init = tf.initialize_all_variables()                                                                             
with tf.Session() as sess:
     sess.run(init)
     print (x.eval())
     print (inputs.eval())

输出结果：

[[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.]]
[[1.25 1.25 0.   1.25 1.25 1.25 1.25 1.25 1.25 0.  ]
 [0.   1.25 1.25 1.25 1.25 1.25 1.25 1.25 1.25 1.25]
 [1.25 1.25 1.25 1.25 1.25 1.25 1.25 1.25 1.25 1.25]
 [1.25 1.25 1.25 1.25 1.25 0.   1.25 1.25 1.25 1.25]
 [1.25 1.25 1.25 1.25 1.25 0.   1.25 1.25 0.   1.25]
 [1.25 1.25 1.25 1.25 1.25 0.   0.   1.25 1.25 1.25]
 [0.   1.25 1.25 0.   1.25 1.25 1.25 0.   1.25 0.  ]
 [1.25 0.   0.   1.25 1.25 1.25 1.25 1.25 1.25 1.25]
 [1.25 1.25 1.25 0.   1.25 1.25 1.25 0.   0.   0.  ]
 [1.25 1.25 0.   0.   0.   0.   1.25 1.25 1.25 1.25]]

加入 noise：

import os
import numpy as np
import tensorflow as tf


x = tf.Variable(tf.ones([3,3,3]))

inputs = tf.nn.dropout(x, 0.5,[3,1,3])                                                                           


init = tf.initialize_all_variables()
with tf.Session() as sess:
     sess.run(init)
     print (x.eval())
     print (inputs.eval())

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

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

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