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)
#定义每个批次的大小
batch_size=50
#计算一共有多少个批次
n_batch=mnist.train.num_examples//batch_size#总的数量整除批次大小
#定义两个placeholder
x=tf.placeholder(tf.float32,[None,784])#行是批次是任意的值,784向量列
y=tf.placeholder(tf.float32,[None,10])#标签是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))
#使用梯度下降
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向量中,返回一维张量当中最大的值在的位置
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))#将布尔转化为浮点然后再求平均值
with tf.Session() as sess:
sess.run(init)
for epoch in range(51):
for batch in range(n_batch):
[batch_xs,batch_ys]=mnist.train.next_batch(batch_size)#获得下一百张图片
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("iter"+str(epoch)+"Testing accuracy"+str(acc))