TensorFlow--Dropout防止过拟合现象

使用带3个隐藏层的神经网络

为了防止过拟合现象的发生，对于keep_prob可以设置为0.7/0.8等

以

#-*-coding:utf-8-*-
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#载入数据集
minist = input_data.read_data_sets('MNIST_data',one_hot=True)
#每个批次的大小
batch_size = 100
#一共有多少批次
n_batch = minist.train.num_examples//batch_size
#定义两个placeholder
#当用训练集定义每批次100个时，x为[100,784]的矩阵，y为[100,10]的矩阵
#x,y 这里虽然是变量，但是只是针对数据集批次的变量，真正的要训练的模型参数是权重和偏置值
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
# w = tf.Variable(tf.zeros([784,10]))
# b = tf.Variable(tf.zeros([10]))
# prediction = tf.nn.softmax(tf.matmul(x,w)+b)

#增加神经网络隐藏层
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)

#二次代价函数
loss = tf.reduce_mean(tf.square(y - prediction))
#使用交叉熵代价函数
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
#使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

init = tf.global_variables_initializer()
#结果存放在一个布尔数组里面
#tf.argmax 返回一维张量中最大值所在的位置
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))
#求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(21):
        for batch in range(n_batch):
            #训练是用的训练集，按照分批次来做
            batch_xs,batch_ys = minist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:1.0})
        #此处的准确率是针对现有的参数，对于所有的测试集(测试图片，测试标签）来计算准确率
        acc_test = sess.run(accuracy,feed_dict={x:minist.test.images,y:minist.test.labels,keep_prob:1.0})
        acc_train = sess.run(accuracy,feed_dict={x:minist.train.images,y:minist.train.labels,keep_prob:1.0})
        print('iterator: '+str(epoch)+' accuracy_test: '+str(acc_test)+', accuracy_train: '+str(acc_train))

keep_prob = 1.0 时，即不dropout 神经元时的运行结果为：

keep_prob = 0.8 时，运行结果为：

可以看到迭代速度下降了，但是测试集准确率和训练及准确率的差变小了