Tensorflow入门5-Mnist手写数字识别（CNN）

一、mnist数据集下载
链接：https://pan.baidu.com/s/1cqLjY790dzJXr1My6Yt4VQ
提取码：nobn
将数据集放在项目文件夹下，每次运行无需下载，节省时间
#input_data读取的是压缩包，所以minist四个文件夹无需解压
使用下面语句调用mnist数据集

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

二、使用卷积神经网络对MNIST进行分类预测
使用卷积>>池化>>卷积>>池化>>两层神经网络>>softmax多分类器

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

#计算准确率
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
    
#权重初始化
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)
    
#偏置系数初始化
def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)
    
#定义卷积层
def conv2d(x, W):
    # stride [1, x_movement, y_movement, 1]
    # Must have strides[0] = strides[3] = 1
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
    #其中strides(batch,heihgt,weight,channels)batch和channnels为1指不对其进行操作。height和weight为1是每步步长都为1.格式为[1,x_movement,y_movement.1]
    
#定义池化层
def max_pool_2x2(x):
    # stride [1, x_movement, y_movement, 1]
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

# 使用占位符定义输入数据
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])#-1表示自动计算维度，28*28是高和宽，1是灰度
#print(x_image.shape)#[n_sanples,28,28,1]

## conv1 layer ##
W_conv1=weight_variable([5,5,1,32])#patch5*5,1个通道,32个过滤器
b_conv1=bias_variable([32])
h_conv1=tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)#output size(28*28*32)
h_pool1=max_pool_2x2(h_conv1)#output size(14*14*32)

## conv2 layer ##
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)

## func1 layer 全连接层##
W_fc1=weight_variable([7*7*64,1024])    #1024个神经元个数
b_fc1=bias_variable([1024])
#[n_samples,7,7,64]->>[n_samples,7*7*64]
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)
h_fc1_drop=tf.nn.dropout(h_fc1,keep_prob)   #使用dropout防止过拟合，系数keep_prob设置为0.5

## func2 layer ##
W_fc2=weight_variable([1024,10])
b_fc2=bias_variable([10])
#输出perdiction，使用softmax多分类器
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损失函数
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)   #Adam优化器,学习率为0.0004

init = tf.global_variables_initializer()
with tf.Session() as sess:    
    sess.run(init)
    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[:1000], mnist.test.labels[:1000]))

最终运行的结果，最终准确率在0.964
0.105
0.75
0.846
0.889
0.898
0.91
0.922
0.926
0.937
0.944
0.947
0.949
0.946
0.957
0.955
0.958
0.963
0.961
0.964
0.964