tensorflow实战之全连接神经网络实现mnist手写字体识别

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

#参数设置
input_nodes = 784  #输入节点数
output_nodes = 10  #输出节点数
layer1_nodes = 500 #隐层节点数
bitch_size = 100 #每次训练包含的数据个数
learning_rate = 0.8 #初始学习率
learning_rate_deacy = 0.99 #学习率衰减率
l2_regulation = 0.0001 #l2正则化系数
moving_rate_deacy = 0.99 #滑动模型那个衰减率
train_num = 10000

#前向传播，variable_average平均滑动模型参数
def inference(x,variable_average,w1,b1,w2,b2):
    
    if variable_average == None:    
        layer1 = tf.nn.relu(tf.matmul(x,w1)+b1)
        return tf.matmul(layer1,w2)+b2
    
    else:
        layer1 = tf.nn.relu(tf.matmul(x,variable_average.average(w1))+variable_average.average(b1))
        return tf.matmul(layer1,variable_average.average(w2))+variable_average.average(b2)

def train(mnist): 
    
    #features and labels
    x = tf.placeholder(tf.float32,[None,784])
    y_ = tf.placeholder(tf.float32,[None,10])
    
    #参数初始化
    w1 = tf.Variable(tf.truncated_normal([input_nodes,layer1_nodes],stddev=0.1))
    b1 = tf.Variable(tf.constant(0.1,shape=[layer1_nodes]))
    w2 = tf.Variable(tf.truncated_normal([layer1_nodes,output_nodes],stddev=0.1))
    b2 = tf.Variable(tf.constant(0.1,shape=[output_nodes]))
    
    #不使用平均化滑动模型的前向传播结果
    y = inference(x,None,w1,b1,w2,b2)
    
    #平均滑动模型
    global_step = tf.Variable(0,trainable=False)
    #定义一个平均滑动模型的类
    variable_average = tf.train.ExponentialMovingAverage(0.99,global_step)
    #定义一个平均华东模型操作，应用给所有可训练变量
    variable_average_op = variable_average.apply(tf.trainable_variables())
    #使用平均化滑动模型的前向传播结果
    average_y = inference(x,variable_average,w1,b1,w2,b2)
    
    #交叉熵损失函数
    cost_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y,labels=tf.arg_max(y_,1))
    cost_entropy_mean = tf.reduce_mean(cost_entropy)
    
    #l2正则化
    regulations = tf.contrib.layers.l2_regularizer(0.0001)
    l2_regulation = regulations(w1)+regulations(w2)
    
    #带有正则化的损失函数作为最终的损失函数
    loss = cost_entropy_mean+l2_regulation
    
    #学习率衰减
    learning_rate_deacy = tf.train.exponential_decay(learning_rate=0.8,global_step=global_step,decay_steps=100,
                                                     decay_rate=0.99)
    #训练
    train_step = tf.train.GradientDescentOptimizer(learning_rate_deacy).minimize(loss,global_step=global_step)
    
    #tf.group函数保证再一次迭代中，参数的train和参数的平均滑动都被执行
    train_op = tf.group(train_step,variable_average_op)
    
    #准确率
    correct_predict = tf.equal(tf.argmax(average_y,1),tf.argmax(y_,1))
    accuracy = tf.reduce_mean(tf.cast(correct_predict,tf.float32))
    
    #定义一个初始化的操作
    init_op = tf.global_variables_initializer()

    with tf.Session() as sess: 
        init_op.run()
        validation_feed = {x:mnist.validation.images,y_:mnist.validation.labels} #验证数据
        test_feed = {x:mnist.test.images,y_:mnist.test.labels} #测试数据
        for i in range(train_num):
            if i%1000 == 0:
                validation_acc = sess.run(accuracy,feed_dict=validation_feed)
                print('训练%d次验证集准确率是%g'%(i+1,validation_acc))
            #训练数据
            x_data,y_data = mnist.train.next_batch(bitch_size)
            train_feed = {x:x_data,y_:y_data}
            sess.run(train_op,feed_dict=train_feed)
        #测试精度
        test_acc = sess.run(accuracy,feed_dict=test_feed)
        print('测试精度是%g'%test_acc)

mnist = input_data.read_data_sets('data',one_hot=True)
train(mnist)