import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)
#每个批次的大小和总共有多少个批次
batch_size = 100
n_batch = mnist.train.num_examples // batch_size
#定义两个placeholder
x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])
#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)
#二次代价函数
#loss = tf.reduce_mean(tf.square(y-prediction))
#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)
#初始化变量
init = tf.global_variables_initializer()
#结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))#argmax返回一维张量中最大的值所在的位置
#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(20):
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})
acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
print("epoch " + str(epoch)+ " acc " +str(acc))
这是一个简单的结构,输入到输出,没有隐层,可以添加隐层。
# 定义神经网络中间层
Weights_L1 = tf.Variable(tf.random_normal([784,100]))
biases_L1 = tf.Variable(tf.zeros([100]))
Wx_plus_b_L1 = tf.matmul(x, Weights_L1)+biases_L1
L1 = tf.nn.tanh(Wx_plus_b_L1)
#定义神经网络输出层
Weights_L2 = tf.Variable(tf.random_normal([100, 10]))
biases_L2 = tf.Variable(tf.zeros([10]))
Wx_plus_b_L2 = tf.matmul(L1, Weights_L2) + biases_L2
prediction = tf.nn.softmax(Wx_plus_b_L2)
激活函数为线性函数----------->代价函数选择二次代价函数
loss = tf.reduce_mean(tf.square(y-prediction))
激活函数为“S"型(sigmod; tanh)---------------->代价函数选择交叉熵代价函数
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))