Tensorflow_dropout解决过拟合问题

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#载入数据集;对数据集分batch并计算总共有多少batch
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)
batch_size = 100
n_batch = mnist.train.num_examples // batch_size

#定义两个placeholder, keep_prob控制有多少个网络节点用来训练模型
x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])
keep_prob=tf.placeholder(tf.float32)

#创建一个简单的神经网络
W1 = tf.Variable(tf.truncated_normal([784,2000],stddev=0.1))
b1 = tf.Variable(tf.zeros([2000])+0.1)
L1 = tf.nn.tanh(tf.matmul(x,W1)+b1)
L1_drop = tf.nn.dropout(L1,keep_prob) 

W2 = tf.Variable(tf.truncated_normal([2000,2000],stddev=0.1))
b2 = tf.Variable(tf.zeros([2000])+0.1)
L2 = tf.nn.tanh(tf.matmul(L1_drop,W2)+b2)
L2_drop = tf.nn.dropout(L2,keep_prob) 

W3 = tf.Variable(tf.truncated_normal([2000,1000],stddev=0.1))
b3 = tf.Variable(tf.zeros([1000])+0.1)
L3 = tf.nn.tanh(tf.matmul(L2_drop,W3)+b3)
L3_drop = tf.nn.dropout(L3,keep_prob) 

W4 = tf.Variable(tf.truncated_normal([1000,10],stddev=0.1))
b4 = tf.Variable(tf.zeros([10])+0.1)
prediction = tf.nn.softmax(tf.matmul(L3_drop,W4)+b4)

#交叉熵代价函数并用梯度下降法进行训练
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

#初始化变量
init = tf.global_variables_initializer()

#结果存放在一个布尔型列表中,并计算准确率 argmax()返回一维向量中最大值所在的位置
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(31):
        for batch in range(n_batch):
            batch_xs,batch_ys =  mnist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:0.7}) #0.7的网络节点训练
        #keep_prob:1.0 表示所有的网络节点用来测试
        test_acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
        train_acc = sess.run(accuracy,feed_dict={x:mnist.train.images,y:mnist.train.labels,keep_prob:1.0})
        print("Iter " + str(epoch) + ",Testing Accuracy " + str(test_acc) +",Training Accuracy " + str(train_acc))

正常情况下，用训练集来测试和用测试集来测试的差异并不是太大，但是这个试验中差异却很大，这就是过拟合导致的。

过拟合一般出现在这样的情况下：待训练的网络结构复杂，这就会使参数太多，但是训练数据不足，从而出现过拟合。

可以通过增加数据集的方法，或者dropout方法解决。