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

def weight_variable(shape):
    initial = tf.truncated_normal(shape,stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0,1,shape=shape)
    return tf.Variable(initial)

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

def max_pool_2x2(x):
    return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')


# 预处理
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
xs = tf.placeholder(tf.float32,[None,784])
ys = tf.placeholder(tf.float32,[None,10])
keep_prob = tf.placeholder(tf.float32)

# 第一层卷积
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(xs,[-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

# 第二层卷积
W_conv2 = weight_variable([5,5,32,64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2)+b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

# 第一层全连接层
W_fc1 = weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024])
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)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)

# 第二层全连接层
W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2)

# 训练模型
cross_entropy = -tf.reduce_sum(ys*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

# 概率计算
correct_prediction = tf.equal(tf.argmax(y_conv,1),tf.argmax(ys,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

for i in range(2001):
    batch = mnist.train.next_batch(50)
    sess.run(train_step,feed_dict={xs:batch[0],ys:batch[1],keep_prob:0.5})

    if i%100==0:
        tests = mnist.test.next_batch(200)
        print(sess.run(accuracy,feed_dict={xs:tests[0],ys:tests[1],keep_prob:1.0}))