Tensorflow学习（三）——卷积神经网络应用于MNIST数据集分类

编写一个简单的CNN实现MNIST数据集分类（代码如下）

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

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
batch_size = 100
num_batch = mnist.train.num_examples // batch_size


# 初始化权值
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)  # 生成一个截断正态分布
    return tf.Variable(initial)


# 初始化偏置值
def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)


# 卷积层
def conv2d(x, W):
    """
    tf.nn.conv2d()参数说明 --->
    x: 输入tensor的形状，四维变量，[batch, in_height, in_width, in_channels]
    W: 卷积核，形状如下[filter_height, filter_width, in_channels, out_channels]
    strides: 卷积运算步长，strides[0]=1，strides[3]=1，strides[1]代表x方向步长，strides[2]代表y方向步长
    padding: padding方式，即边界处理方式，'SAME' OR 'VALID'
    """
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')


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


x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
# 改变x格式为4维向量[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值
W_conv1 = weight_variable([5, 5, 1, 32])    # 说明：5*5的卷积采样窗口，使用32个卷积核从1个平面抽取特征
b_conv1 = bias_variable([32])
# 把x_image和权值向量进行卷积，再加上偏置值，激活函数使用:relu()
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
# 第二个卷积层
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)

"""
28*28的图片第一次卷积以后依然是28*28，第一次池化以后变为14*14，
第二次卷积时不改变形状，依然时14*14，第二次池化以后则变为7*7，
经过上面的卷积和池化操作以后，得到64张7*7的特征平面.
"""
# 初始化第一个全连接层
W_fc1 = weight_variable([7*7*64, 1024])     # 与特征平面相连的神经元有1024个
b_fc1 = bias_variable([1024])
# 把池化层2的输出扁平化为1维
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
# 第一个全连接层输出
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# dropout
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# 第二个全连接层（输出）
w_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, w_fc2) + b_fc2)

# 交叉熵代价函数
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y, logits=prediction))
train_step = tf.train.AdamOptimizer(0.0001).minimize(loss)
# 准确率计算
correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for epoch in range(21):
        for batch in range(num_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' + str(epoch) + ', testing accuracy:' + str(acc))