（四）Tensorflow学习之旅——MNIST分类的卷积神经网络CNN示例

一个比较简单的CNN模型：

输入：28*28，需要将输入数据reshape成28*28

隐层1：32个神经元，卷积核5*5，池化2*2最大池化，卷积后特征图大小不变，池化后特征图为14*14，RELU

隐层2：64个神经元，卷积核5*5，池化2*2最大池化，卷积后特征图大小不变，池化后特征图为7*7，RELU

                展开7*7的图像为49维向量，共7*7*64维

全连接层：1024个神经元，这里的权重是[7*7*64,1024]，矩阵乘法，RELU

droupout：防止过拟合，tf.nn.dropout()

输出：10分类的softmax分类器



# mnist 两层卷积CNN 分类器
#jhj python 3.5

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

import tensorflow as tf
sess = tf.InteractiveSession()

def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1) #截断正态分布 方差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')

#shape的None代表了没有指定张量的shape，可以feed任何shape的张量，在这里指batch的大小未定。
x = tf.placeholder('float',[None,784])
y_ = tf.placeholder('float',[None,10])
#第一层卷积池化
W_conv1 = weight_variable([5, 5, 1, 32]) #1是通道数
b_conv1 = bias_variable([32])

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

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

#第二层卷积池化
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)

#密集连接层 将h_pool2展开成向量
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)

#dropout
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#接一个10分类的softmax
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)

#训练和评估模型 adaam优化梯度下降法
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
sess.run(tf.initialize_all_variables())

for i in range(20000):
batch = mnist.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x:batch[0], y_: batch[1], keep_prob: 1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

#测试
print("test accuracy %g"%accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))