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

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)\
#每个批次大小
batch_size = 100
#计算一共有多少批次
n_batch = mnist.train.num_examples // batch_size
#初始化权值
def Weight_Variable(shape):
    W = tf.truncated_normal(shape, stddev=0.1)#生成一个截断的正态分布
    return tf.Variable(W)
#初始化偏置
def bias_Variable(shape):
    b = tf.zeros(shape) + 0.1
    return tf.Variable(b)
#卷积层
def conv2d(x, W):
    # x input tensor of shape '[batch, in_height, in_width, in_channels]'
    # w filter/kernel tensor of shape [filter_height, filter_width, in_channels, out_channels]
    # strides[0] = strides[3] = 1, strides[1]代表x方向步长, strides[2]代表y方向步长
    # padding: 'SAME' or 'VALID'
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
#池化层
def max_pooling_2x2(x):
    # ksize [1, x, y, 1]
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
#定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
#改变x的格式为4D的向量 [batch, in_height, in_width, in_channels]
x_image = tf.reshape(x, [-1, 28, 28, 1])

#初始化第一个卷积层的权值和偏置
W_conv1 = Weight_Variable([5, 5, 1, 32])
b_conv1 = bias_Variable([32])

#把x_image和权值向量进行卷积，再加上偏置值，然后应用于relu激活函数
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pooling_2x2(h_conv1) # 进行max-pooling

#初始化第二个卷积层的权值和偏置
W_conv2 = Weight_Variable([5, 5, 32, 64])
b_conv2 = bias_Variable([64])

#把h_pool1和权值向量进行卷积，再加上偏置值，然后应用于relu激活函数
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pooling_2x2(h_conv2)

# 28*28的图片第一次卷积之后还是28*28， 第一次池化之后变成 14*14
# 第二次卷积之后为 14*14， 第二次池化之后变为 7*7
# 经过上面操作之后得到 64张 7*7的平面

#初始化第一个全连接层的权值
W_fc1 = Weight_Variable([7*7*64, 1024]) # 上一层有 7*7*64 个神经元， 全连接层有1024个神经元
b_fc1 = bias_Variable([1024])

# 把第二个池化层的输出扁平为 1维
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
# 求第一个全连接层的输出
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

# keep_prob用来表示神经元的输出概率
keep_prob = tf.placeholder(tf.float32)
h_fc1_dropout = tf.nn.dropout(h_fc1, keep_prob)

# 初始化第二个全连接层
W_fc2 = Weight_Variable([1024, 10])
b_fc2 = bias_Variable([10])

#计算输出
predictions = tf.matmul(h_fc1_dropout, W_fc2) + b_fc2

#交叉熵代价函数
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=predictions))
# 使用adamOptimizer优化
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
# 结果存放在一个列表中
correct = tf.equal(tf.argmax(y, 1), tf.argmax(predictions, 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, tf.float32))

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for epoch in range(21):
        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})

        acc = sess.run(accuracy, feed_dict={x:mnist.test.images, y:mnist.test.labels, keep_prob:1.0})

        print("Iter: epoch" + str(epoch) + "testing acc: " + str(acc))