tensorflow实战之LeNet-5实现mnist手写字体识别

import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data#用mnist数据训练

#input代表输入数据
#train代表是否是训练过程
#regulation代表是否加入正则化


def inference(input,train,regulation):
    #第一层卷积，卷积核size为[5,5,1,6]
    with tf.variable_scope('conv1'):
        weight1 = tf.get_variable('weight1',shape=[5,5,1,6],initializer=tf.truncated_normal_initializer(stddev=0.1))
        bias1 = tf.get_variable('bias1',shape=[6],initializer=tf.constant_initializer(0.0,dtype=tf.float32))
        conv1 = tf.nn.conv2d(input,weight1,strides=[1,1,1,1],padding='VALID')
        activation1 = tf.nn.relu(tf.nn.bias_add(conv1,bias1))
    #第一层池化
    with tf.variable_scope('pool1'):
        pool1 = tf.nn.max_pool(activation1,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
    #第二层卷积,卷积核size为[5,5,6,16]
    with tf.variable_scope('conv2'):
        weight2 = tf.get_variable('weight2',shape=[5,5,6,16],initializer=tf.truncated_normal_initializer(stddev=0.1))
        bias2 = tf.get_variable('bias2',shape=[16],initializer=tf.constant_initializer(0.0,dtype=tf.float32))
        conv2 = tf.nn.conv2d(pool1,weight2,strides=[1,1,1,1],padding='VALID')
        activation2 = tf.nn.relu(tf.nn.bias_add(conv1,bias2))
    #第二层池化
    with tf.variable_scope('pool2'):
        pool2 = tf.nn.max_pool(activation2,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
    #把第二层池化层变为全连接层       
    pool2_shape = pool2.get_shape().as_list()
    nodes = pool2_shape[1] * pool2_shape[2] * pool2_shape[3]
    pool2_reshape = tf.reshape(pool2,[-1,nodes])
    #第一层全连接层
    with tf.variable_scope('pc1'):
        weight3 = tf.get_variable('weight3',shape=[nodes,120],initializer=tf.truncated_normal_initializer(stddev=0.1))
        #判断是否有正则化
        if regulation != None:
            tf.add_to_collection('loss_',regulation(weight3))
        b1 = tf.get_variable('bais',shape=[120],initializer=tf.constant_initializer(0.1))
        pc1 = tf.matmul(pool2_reshape,weight3)+ b1
        activation3 = tf.nn.relu(pc1)
        #判断是否为训练过程，是的话加入dropout
        if train != None:
            activation3 = tf.nn.dropout(activation3,0.8)
    with tf.variable_scope('pc2'):
        weight4 = tf.get_variable('weight4',shape=[120,84],initializer=tf.truncated_normal_initializer(stddev=0.1))
        #判断正则化
        if regulation != None:
            tf.add_to_collection('loss_',regulation(weight4))
        b2 = tf.get_variable('bais2',shape=[84],initializer=tf.truncated_normal_initializer(stddev=0.1))
        pc2 = tf.matmul(activation3,weight4) + b2
        activation4 = tf.nn.relu(pc2)
         #判断是否为训练过程，是的话加入dropout
        if train != None:
            activation4 = tf.nn.dropout(activation4,0.8)
    with tf.variable_scope('pc3'):
        weight5 = tf.get_variable('weight5',shape=[84,10],initializer=tf.truncated_normal_initializer(stddev=0.1))
        #判断正则化
        if regulation != None:
            tf.add_to_collection('loss_',regulation(weight5))
        b3 = tf.get_variable('b3',shape=[10],initializer=tf.truncated_normal_initializer(stddev=0.1))
        pc3 = tf.matmul(activation4,weight5)+b3
        activation6 = tf.nn.relu(pc3)
    return activation6

#用mnist数据集训练网络
def train(mnist):
    x = tf.placeholder(tf.float32,[None,28,28,1])
    y_ = tf.placeholder(tf.float32,[None,10])
    #训练过程给到正则化
    regulation = tf.contrib.layers.l2_regularizer(0.0001)
    #前向传播的值
    y = inference(x,train=1,regulation=regulation)
    #迭代轮数
    global_step = tf.Variable(0,trainable=False)
    #滑动平均
    average_moving_deacy = tf.train.ExponentialMovingAverage(0.99,global_step)
    average_moving_deacy_op = average_moving_deacy.apply(tf.trainable_variables())
    #交叉熵损失函数
    entory_loss = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.arg_max(y_,1),logits=y)
    entory_loss_mean = tf.reduce_mean(entory_loss)
    #带正则化的损失函数
    loss = entory_loss_mean + tf.add_n(tf.get_collection('loss_'))
    #学习率衰减
    learning_rate_deacy = tf.train.exponential_decay(0.8,global_step=global_step,decay_steps=mnist.train.num_examples/100,decay_rate=0.99)
    #训练
    train_step = tf.train.GradientDescentOptimizer(learning_rate_deacy).minimize(loss,global_step=global_step)
    #滑动平均和训练过程同时进行
    train_op = tf.group(train_step,average_moving_deacy_op)
    #初始化
    init_op = tf.global_variables_initializer()
    #定义模型保存类
    saver = tf.train.Saver()
    with tf.Session() as sess:
        init_op.run()
        #总共训练10000次
        for i in range(30000):
            #训练数据
            x_data,y_data = mnist.train.next_batch(batch_size=100)
            #把输入数据的格式转化为网络需要的格式
            x_data = np.reshape(x_data,[100,28,28,1])
            train_feed = {x:x_data,y_:y_data}
            #返回损失值
            _,loss_values = sess.run([train_op,loss],feed_dict=train_feed)
            #没训练1000次返回一次损失值，并保存一次模型
            if i % 1000 == 0:
                print('训练%d次后当前损失值为%g'%(i+1,loss_values))
                saver.save(sess,'model/model.ckpt')

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

训练结果：

#用mnist数据集来测试
def test(x_data,y_data):
    
    x = tf.placeholder(tf.float32,[None,28,28,1])
    y_ = tf.placeholder(tf.float32,[None,10])
    #前向传播
    y = inference(x,None,None)
    #精确度
    accuracy = tf.reduce_mean(tf.cast(tf.equal(tf.arg_max(y_,1),tf.arg_max(y,1)),tf.float32))
    #滑动平均
    ema = tf.train.ExponentialMovingAverage(decay=0.99)
    variables_restore = ema.variables_to_restore()
    #加载模型类
    saver = tf.train.Saver(variables_restore)
    with tf.Session() as sess:
        #查找最新模型
        ckpt = tf.train.get_checkpoint_state('model/')
        x_data = np.reshape(x_data,[-1,28,28,1])
        test_feed = {x:x_data,y_:y_data}
        if ckpt and ckpt.model_checkpoint_path:
            saver.restore(sess,'model/model.ckpt')
            acc = sess.run(accuracy,feed_dict=test_feed)
            print('测试集准确率%g'%(acc))
    return acc

准确率为：0.9941

 

欢迎关注公众号“阿甘琐记”，专注机器学习资源分享