1、不使用dropout的方案:

from __future__ import print_function
import tensorflow as tf
from sklearn.datasets import load_digits
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import LabelBinarizer

# load data
digits = load_digits()
X = digits.data
y = digits.target
y = LabelBinarizer().fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.3)


def add_layer(inputs, in_size, out_size, layer_name, activation_function=None, ):
    # add one more layer and return the output of this layer
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, )
    Wx_plus_b = tf.matmul(inputs, Weights) + biases

    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b, )
    tf.histogram_summary(layer_name + '/outputs', outputs)
    return outputs


# define placeholder for inputs to network

xs = tf.placeholder(tf.float32, [None, 64])  # 8x8
ys = tf.placeholder(tf.float32, [None, 10])

# add output layer
l1 = add_layer(xs,64,50,'l1',activation_function=tf.nn.tanh)
prediction = add_layer(l1, 50, 10, 'l2', activation_function=tf.nn.softmax)

# the loss between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))  # loss
tf.scalar_summary('loss', cross_entropy)
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess = tf.Session()
merged = tf.merge_all_summaries()
# summary writer goes in here
train_writer = tf.train.SummaryWriter("logs/train",sess.graph)
test_writer = tf.train.SummaryWriter("logs/test",sess.graph)

sess.run(tf.initialize_all_variables())

for i in range(500):
    sess.run(train_step, feed_dict={xs: X_train, ys: y_train})
    if i % 50 == 0:
        train_result = sess.run(merged,feed_dict={xs:X_train,ys:y_train})
	test_result = sess.run(merged,feed_dict={xs:X_test,ys:y_test})
	train_writer.add_summary(train_result,i)
	test_writer.add_summary(test_result,i)

说明：

1、因为要可视化训练和测试的loss.所以,必须定义两个文件来写入训练的结果,比如我们将训练和测试的结果分别写入logs/train,logs/test

sess = tf.Session()
merged = tf.merge_all_summaries()
# summary writer goes in here
train_writer = tf.train.SummaryWriter("logs/train",sess.graph)
test_writer = tf.train.SummaryWriter("logs/test",sess.graph)

2、然后,每次迭代训练的过程中,就要分别输出train,test的结果

for i in range(500):
    sess.run(train_step, feed_dict={xs: X_train, ys: y_train})
    if i % 50 == 0:
        train_result = sess.run(merged,feed_dict={xs:X_train,ys:y_train})
        test_result = sess.run(merged,feed_dict={xs:X_test,ys:y_test})
        train_writer.add_summary(train_result,i)
        test_writer.add_summary(test_result,i)

得到的结果：说明test loss 会大于train loss还比较多,有点过拟合的倾向,那么我们接下来就使用dropout来避免过拟合.

二、使用dropout的结果：

from __future__ import print_function
import tensorflow as tf
from sklearn.datasets import load_digits
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import LabelBinarizer

# load data
digits = load_digits()
X = digits.data
y = digits.target
y = LabelBinarizer().fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.3)


def add_layer(inputs, in_size, out_size, layer_name, activation_function=None, ):
    # add one more layer and return the output of this layer
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, )
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    # here to dropout
    Wx_plus_b = tf.nn.dropout(Wx_plus_b, keep_prob)
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b, )
    tf.histogram_summary(layer_name + '/outputs', outputs)
    return outputs


# define placeholder for inputs to network
keep_prob = tf.placeholder(tf.float32)
xs = tf.placeholder(tf.float32, [None, 64])  # 8x8
ys = tf.placeholder(tf.float32, [None, 10])

# add output layer
l1 = add_layer(xs, 64, 50, 'l1', activation_function=tf.nn.tanh)
prediction = add_layer(l1, 50, 10, 'l2', activation_function=tf.nn.softmax)

# the loss between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))  # loss
tf.scalar_summary('loss', cross_entropy)
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess = tf.Session()
merged = tf.merge_all_summaries()
# summary writer goes in here
train_writer = tf.train.SummaryWriter("logs/train", sess.graph)
test_writer = tf.train.SummaryWriter("logs/test", sess.graph)

sess.run(tf.initialize_all_variables())

for i in range(500):
    # here to determine the keeping probability
    sess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 0.5})
    if i % 50 == 0:
        # record loss
        train_result = sess.run(merged, feed_dict={xs: X_train, ys: y_train, keep_prob: 1})
        test_result = sess.run(merged, feed_dict={xs: X_test, ys: y_test, keep_prob: 1})
        train_writer.add_summary(train_result, i)
        test_writer.add_summary(test_result, i)

说明：

1、dropout必须设置概率keep_prob,并且keep_prob也是一个占位符,跟输入是一样的

keep_prob = tf.placeholder(tf.float32)

2、train的时候才是dropout起作用的时候,train和test的时候不应该让dropout起作用

sess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 0.5})

train_result = sess.run(merged, feed_dict={xs: X_train, ys: y_train, keep_prob: 1})
test_result = sess.run(merged, feed_dict={xs: X_test, ys: y_test, keep_prob: 1})

3、tf实现dropout其实,就一个函数,让一个神经元以某一固定的概率失活

def add_layer(inputs, in_size, out_size, layer_name, activation_function=None, ):
    # add one more layer and return the output of this layer
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, )
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    # here to dropout
    Wx_plus_b = tf.nn.dropout(Wx_plus_b, keep_prob)
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b, )
    tf.histogram_summary(layer_name + '/outputs', outputs)
    return output

4、说明：使用dropout之后,训练误差和测试误差类似