【TensorFlow】使用卷积神经网络对MNIST进行分类

import os
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

加载数据

mnist = input_data.read_data_sets('../input',one_hot=True)

Extracting ../input/train-images-idx3-ubyte.gz
Extracting ../input/train-labels-idx1-ubyte.gz
Extracting ../input/t10k-images-idx3-ubyte.gz
Extracting ../input/t10k-labels-idx1-ubyte.gz

参数

batch_size = 128
n_batch = mnist.train.num_examples//batch_size

用于初始化的函数

# 初始化权重
def weight_variable(shape):
    initial = tf.truncated_normal(shape,stddev=0.1)
    return tf.Variable(initial)
# 初始化偏置
def bias_variable(shape):
    initial = tf.constant(0.1,shape=shape)
    return tf.Variable(initial)

卷积层与池化层的定义

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')

定义计算图

x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])
# [batch_size,in_height,in_weight,in_channels]
x_image = tf.reshape(x,[-1,28,28,1])
# 初始化第一个卷积层的权重和偏置
W_conv1 = weight_variable([5,5,1,32]) # 5*5是filter的大小，1是channel，32是filter的个数
b_conv1 = bias_variable([32])

h_conv1 = tf.nn.relu(conv2D(x_image,W_conv1)+b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

# 经过第一次的卷积和池化后输出的tensor为(14*14*32)

# 初始化第二个卷积层的权重和偏置
W_conv2 = weight_variable([5,5,32,64]) # 5*5的filter，32是channel，64是channel的数量
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2D(h_pool1,W_conv2)+b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

# 经过第二次的卷积核池化后输出的tensor为(7*7*64)

# 初始化第一个全连接层的权重和偏置
W_fc1 = weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024])

# 将池化层2的输出扁平化为1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)

# dropout
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的权重和偏置
W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])

# 预测
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2)
# 交叉熵
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
# 优化
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_prediction = tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))
# 准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

训练

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})
        
        test_acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
        print("Iter "+str(epoch)+",Testing accuracy = "+str(test_acc))