import loaddata

import tensorflow as tf

#生成指定大小符合标准差为0.1的正态分布的矩阵

def weight_variable(shape):

    initial = tf.truncated_normal(shape, stddev = 0.1)

    return tf.Variable(initial)

#生成偏移变量

def bias_variable(shape):

    initial = tf.constant(0.1, shape=shape)

    return tf.Variable(initial)

#做W与x的卷积运算，跨度为1，zero-padding补全边界（使得最后结果大小一致）

def conv2d(x, W):

    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

#做2x2的max池化运算，使结果缩小4倍（面积上）

def max_pool_2x2(x):

    return tf.nn.max_pool(x, ksize = [1, 2, 2, 1],

                          strides=[1, 2, 2, 1], padding = 'SAME')

#导入数据

mnist = loaddata.read_data_sets('MNIST_data', one_hot=True)

x = tf.placeholder("float", shape=[None, 784])

y_ = tf.placeholder("float", shape=[None, 10])

#filter取5x5的范围，因为mnist为单色，所以第三维是1，卷积层的深度为32

W_conv1 = weight_variable([5, 5, 1, 32])

b_conv1 = bias_variable([32])

#将输入图像变成28*28*1的形式，来进行卷积

x_image = tf.reshape(x, [-1, 28, 28, 1])

#卷积运算，activation为relu

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)

#池化运算

h_pool1 = max_pool_2x2(h_conv1)

#第二个卷积层，深度为64，filter仍然取5x5

W_conv2 = weight_variable([5, 5, 32, 64])

b_conv2 = bias_variable([64])

#做同样的运算

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)

h_pool2 = max_pool_2x2(h_conv2)

#full-connected层，将7*7*64个神经元fc到1024个神经元上去

W_fc1 = weight_variable([7*7*64, 1024])

b_fc1 = bias_variable([1024])

#将h_pool2（池化后的结果）打平后，进行fc运算

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])

h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

#防止过拟合，fc层进行dropout处理，参数为0.5

keep_prob = tf.placeholder("float")

h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#第二个fc层，将1024个神经元fc到10个最终结果上去（分别对应0~9）

W_fc2 = weight_variable([1024, 10])

b_fc2 = bias_variable([10])

#最后结果

y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

#误差函数使用交叉熵

cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))

#梯度下降使用adam算法

train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

#正确率处理

correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

#初始化

sess = tf.Session()

sess.run(tf.initialize_all_variables())

#进行训练

for i in range(20000):

    batch = mnist.train.next_batch(50)

    if i%100 == 0:

        train_accuracy = sess.run(accuracy, feed_dict = {

            x:batch[0], y_:batch[1], keep_prob : 1.0})

        print("step %d, accuracy %g" % (i, train_accuracy))

    sess.run(train_step, feed_dict={x:batch[0], y_:batch[1], keep_prob:0.5})

#输出最终结果

print(sess.run(accuracy, feed_dict={

    x:mnist.test.images, y_:mnist.test.labels, keep_prob:1.0}))