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

mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
#每个批次的大小
batch_size = 128
#计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size
#定义输入输出
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
lr = tf.Variable(0.001, dtype=tf.float32)
#创建一个简单的神经网络
W1 = tf.Variable(tf.truncated_normal([784, 1000], stddev=0.1))
b1 = tf.Variable(tf.zeros([1, 1000]))
L1 = tf.nn.relu(tf.matmul(x, W1) + b1)
L1_dropout = tf.nn.dropout(L1, keep_prob)
# 第二层
W2 = tf.Variable(tf.truncated_normal([1000, 500], stddev=0.1))
b2 = tf.Variable(tf.zeros([1, 500]))
L2 = tf.nn.relu(tf.matmul(L1_dropout, W2) + b2)
L2_dropout = tf.nn.dropout(L2, keep_prob)
# 第三层
W3 = tf.Variable(tf.truncated_normal([500, 10], stddev=0.1))
b3 = tf.Variable(tf.zeros([1, 10]))
prediction = tf.matmul(L2_dropout, W3) + b3
#定义交叉熵代价函数
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))
#使用梯度下降
train_step = tf.train.AdamOptimizer(lr).minimize(loss)
#初始化变量
init = tf.global_variables_initializer()

#结果存放在一个bool型列表中
correction = 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(correction, tf.float32))

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(50):
        sess.run(tf.assign(lr, 0.001 * (0.95 ** epoch)))
        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})
        lr1 = sess.run(lr)
        acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels, keep_prob: 1.0})
        print("epoch " + str(epoch) + ", accuracy " + str(acc) + ", lr " + str(lr1))