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100张照片
batch_size = 100
#计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size

with tf.name_scope('input'):
    #定义两个placeholder
    x = tf.placeholder(tf.float32,[None,784],name='x_input')
    y = tf.placeholder(tf.float32,[None,10],name='y_input')
    keep_prob=tf.placeholder(tf.float32)
    lr=tf.Variable(1e-3,dtype=tf.float32)

#创建一个简单的神经网络，输入层784个神经元，输出层10个神经元
W1 = tf.Variable(tf.truncated_normal([784,500],stddev=0.1))
b1 = tf.Variable(tf.zeros([500])+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([500,300],stddev=0.1))
b2 = tf.Variable(tf.zeros([300])+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([300,10],stddev=0.1))
b3 = tf.Variable(tf.zeros([10])+0.1)
prediction = tf.nn.softmax(tf.matmul(L2_drop,W3)+b3)

#交叉熵代价函数
#reduce_mean是求平均值
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))

#优化器训练
train_step = tf.train.AdamOptimizer(1e-3).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))#cast是进行数据格式转换，把布尔型转为float32类型

with tf.Session() as sess:
    #执行初始化
    sess.run(init)
    writer=tf.summary.FileWriter('log/',sess.graph)
    #迭代51个周期
    for epoch in range(51):
        sess.run(tf.assign(lr,0.001*(0.95**epoch)))#学习率逐渐减小
        #每个周期迭代n_batch个batch，每个batch为100
        for batch in range(n_batch):
            #获得一个batch的数据和标签
            batch_xs,batch_ys =  mnist.train.next_batch(batch_size)
            #通过feed喂到模型中进行训练
            sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:1.0})
        
        #计算准确率
        learning_rate=sess.run(lr)
        acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
        print("Iter " + str(epoch) + ",Testing Accuracy " + str(acc) + ",Learning rate"+str(learning_rate))