基于CNN的MNIST手写数据集识别

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# number 1 to 10 data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

def compute_accuracy(v_xs, v_ys):
    global prediction
    y_pre = sess.run(prediction, feed_dict={xs:v_xs, keep_prob:1})
    correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
    result = sess.run(accuracy, feed_dict={xs:v_xs,ys:v_ys,keep_prob:1})
    return result

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)

def conv2d(x,W):
    return tf.nn.conv2d(x,W,strides=[1,1,1,1], padding='SAME') #strides是步长,实际上是卷积窗口大小对应feature map，含义：[batch,height,weight,channels]因为在卷积池化过程中不需要对batch和channels进行操作，所以这两个实际上是1


def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME') #第一个和最后一个为1原因同上

# define placeholder foe inputs to network
xs = tf.placeholder(tf.float32, [None,784])# 28x28
ys = tf.placeholder(tf.float32,[None,10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs,[-1,28,28,1]) # 第一个数是batch，意思是有多少个图片，这里含义是有n个28*28，通道为1的图片，n根据传入的参数自己匹配
#-1的原因是reshape会自己计算
#print(x_image.shape)# [n_samples,28,28,1]

##conv1 layer##
W_conv1 = weight_variable([5,5,1,32]) #patch 5x5,in size1,outsize 32
b_conv1 = bias_variable([32]) #32个卷积核
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+ b_conv1) # output size 28x28x32,因为用了same的padding方法
h_pool1 = max_pool_2x2(h_conv1) #输出值 output size 14x14x32
##conv2 layer##
W_conv2 = weight_variable([5,5,32,64]) #patch 5x5,in size32,outsize 64
b_conv2 = bias_variable([64]) #64个卷积核
h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2)+ b_conv2) # output size 14x14x64,因为用了same的padding方法
h_pool2 = max_pool_2x2(h_conv2) #输出值 output size 7x7x64
##func1 layer##
W_fc1 = weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64]) #[n_samples,7,7,64]->>[n_samples,7*7*64]
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)

##func2 layer##
W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2)

# the error between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))#loss
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

sess = tf.Session()
#important step
sess.run(tf.initialize_all_variables())
for i in range(1000):
    batch_xs, batch_ys=mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={xs:batch_xs, ys:batch_ys,keep_prob:0.5})
    if i % 50 == 0:
        print(compute_accuracy(mnist.test.images, mnist.test.labels))

运行准确率：
0.0813
0.7866
0.8754
0.9014
0.9203
0.9273
0.9377
0.9422
0.9469
0.952
0.9521
0.9557
0.957
0.9587
0.9595
0.9635
0.9655
0.9659
0.9682
0.9675