TensorFlow（三）dropout

       运用dropout防止过拟合，还是之前的数据，用tensorboard进行可视化， 如果没用dropout的话， test的loss要比train的loss大，这就是过拟合了，即训练的很好，但是测试的时候效果远比训练的时候差

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

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)     #skleran的划分数据集

def add_layer(inputs, in_size, out_size, layer_name, activation_function=None, ):
    w = tf.Variable(tf.random_normal([in_size, out_size]))
    b = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    Wx_plus_b = tf.matmul(inputs, w) + b;
    Wx_plus_b = tf.nn.dropout(Wx_plus_b, keep_prob)             #加入dropout，相当于去掉一半的数据，防止过拟合
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b, )
    tf.summary.histogram(layer_name + '/outputs', outputs)
    return outputs

keep_prob = tf.placeholder(tf.float32)              #保持率
xs = tf.placeholder(tf.float32, [None, 64])
ys = tf.placeholder(tf.float32, [None, 10])

l1 = add_layer(xs, 64, 50, 'l1', activation_function=tf.nn.tanh)            #第一层
prediction = add_layer(l1, 50, 10, 'l2', activation_function=tf.nn.softmax)     #第二层

cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction), reduction_indices=[1]))       #loss函数
tf.summary.scalar('loss', cross_entropy)
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)     #训练，梯度下降

sess = tf.Session()

merged = tf.summary.merge_all()         #将所有summary保存在磁盘，以便tensorboard显示
train_writer = tf.summary.FileWriter("logs/train", sess.graph)      #事件文件所在目录，第二个参数是事件文件要记录的图
test_writer = tf.summary.FileWriter("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, keep_prob: 0.5})      #把保留率设为0.5，即只留一半
    if i % 50 == 0 :
        train_result = sess.run(merged, feed_dict={xs: X_train, ys: y_train, keep_prob: 1})     #把训练结果保存，以便tensorboard显示
        test_result = sess.run(merged, feed_dict={xs: X_test, ys: y_test, keep_prob: 1})        #把测试结果保存，以便tensorboard显示
        train_writer.add_summary(train_result, i)           #每50次记一下
        test_writer.add_summary(test_result, i)

这样在logs文件夹下面生成了train和test文件夹，里面分别有一个文件，启动命令行，切换的..\venv\环境下，输入

tensorboard --logdir=logs

复制最后的URL，放在浏览器上，就能显示函数图像了。