tensorflow实现简单的卷积神经网络

import input_data
import tensorflow as tf

mnist = input_data.read_data_sets("D:\python\project\deeplearn_dairy\AutoEncoder\MNIST_data", one_hot=True)
# 创建默认的Interactive Session
sees = tf.InteractiveSession()
# 设置函数用来实现很多权重和偏置的创建，并且给权重设置一些随机噪声来打破完全对称，使用截断正态分布噪声
# 标准差为0.1。同时因为使用RELU，也给偏置加入一些正值来避免死亡节点
def weight_Variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def bias_Vraiable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

# 接下来创建卷积层和池化层
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')

x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
x_image = tf.reshape(x, [-1, 28, 28, 1])

# 定义第一个卷积层
w_conv1 = weight_Variable([5, 5, 1, 32])
b_conv1 = bias_Vraiable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, w_conv1) + b_conv1)
h_pool1 = max_pool_2X2(h_conv1)

# 定义第二个卷积层
w_conv2 = weight_Variable([5, 5, 32, 64])
b_conv2 = bias_Vraiable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, w_conv2) + b_conv2)
h_pool2 = max_pool_2X2(h_conv2)

w_fc1 = weight_Variable([7 * 7 * 64, 1024])
b_fc1 = bias_Vraiable([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)

# 使用dropout函数来减轻过拟合
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# 接下来将dropout链接到softmax层
w_fc2 = weight_Variable([1024, 10])
b_fc2 = bias_Vraiable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, w_fc2) + b_fc2)

# 接下来定义损失函数,使用Adam优化器，并且给予较小的学习率
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

# 定义评测准确率
correct_prediction = tf.equal(tf.arg_max(y_conv, 1), tf.arg_max(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

# 开始训练
tf.global_variables_initializer().run()
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 is %g" %(i, train_accuracy))
    train_step.run(feed_dict={x:batch[0], y_:batch[1], keep_prob:0.5})

# 计算整体准确率
print("test accuracy %g" % accuracy.eval(feed_dict={x:mnist.test.images, y_:mnist.test.labels, keep_prob:1.0}))