5.2tensorflow实现简单的卷积神经网络

数据集：mnist
预计准确率：99.2%
结构：2个卷积层，1个全连接层

#!/usr/bin/env python
# coding: utf-8
#载入数据集
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
sess = tf.InteractiveSession()

#初始化函数
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)
    
#卷积，池化函数
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])  #特征
y_ = tf.placeholder(tf.float32, [None, 10]) #真是的label
x_image = tf.reshape(x, [-1,28,28,1])
#-1:样本数量不固定； 28，28:图像尺寸； 1:颜色通道；

#第一个卷积层
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
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)

#全连接层
W_fc1 = weight_variable([7*7*64, 1024])  #[图片尺寸， 隐含节点数量]
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层
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#Sofemax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)

#损失函数cross entropy, 优化器Adam
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)

#准确率
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(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%1000 == 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})
print("test accuracy %g"%accuracy.eval(feed_dict={x:mnist.test.images, y_:mnist.test.labels, keep_prob:1.0}))

运行结果：
step 0, training accuracy 0.06
step 1000, training accuracy 0.9
step 2000, training accuracy 0.94
step 3000, training accuracy 0.98
step 4000, training accuracy 1
step 5000, training accuracy 1
step 6000, training accuracy 1
step 7000, training accuracy 1
step 8000, training accuracy 1
step 9000, training accuracy 1
step 10000, training accuracy 0.96
step 11000, training accuracy 1
step 12000, training accuracy 1
step 13000, training accuracy 0.98
step 14000, training accuracy 1
step 15000, training accuracy 1
step 16000, training accuracy 1
step 17000, training accuracy 1
step 18000, training accuracy 1
step 19000, training accuracy 1
test accuracy 0.9905