本文基于Tensorflow搭建了一个卷积神经网络框架，用于对tensorflow中自带的mnist手写字体识别数据集。mnist手写字体识别几乎是入门深度学习必学的一个例子。本文搭建的框架组成依次为：卷积层1、池化层1、卷积层2、池化层2、全连接层1、全连接层2。利用AdamOptimizer优化器来优化模型，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)
#每个批次的大小
batch_size = 100
#计算一共有多少个批次
n_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
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
#卷积层
def conv2d(x, W):
#strides[0] = strides[3] = 1.strides[1]代表x方向的步长，strides[2]代表y的步长
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
#池化层,池化单元的大小ksize[1, x, y, 1]
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2,2 ,1], strides=[1, 2, 2, 1], padding='SAME')
#定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
#改变x的格式转为4D的向量
x_image = tf.reshape(x, [-1, 28, 28, 1])
#初始化第一个卷积层的权值和偏置，采用5*5的采样窗口，32个卷积核
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
#将x_image和权值向量进行卷积，加上偏置，应用于relu激活函数
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
#初始化第二个卷积层的权值和偏置,5*5采样窗口，64个卷积核
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = weight_variable([64])
#第二层卷积、池化操作
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
#28*28的图片第一次卷积后还是28*28，池化后变为14*14；第二次卷积后是14*14，池化后是7*7
#初始化第一个全连接层的权值
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
#将池化层的输出扁平化为一维
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
#第一个全连接层的输出
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
#设置drop_out
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#初始化第二个全连接层
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
#计算输出
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
#交叉熵代价函数
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))
#使用AdamOptimizer进行优化,传入学习率与损失值
train_step = tf.train.AdamOptimizer(0.0001).minimize(cross_entropy)
#结果预测，得出布尔列表
data_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
#求准确率
accuracy = tf.reduce_mean(tf.cast(data_prediction, tf.float32))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(21):
for batch in range(n_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})
print("lter" + str(epoch)+', Testing Accuracy=' + str(acc))