Tensorflow入门实战-mnist手写体识别

'''
tensorflow 教程
mnist样例
'''
import tensorflow as tf 
from tensorflow.examples.tutorials.mnist import input_data

#参数设置
INPUT_NODE=784
OUTPUT_NODE=10
LAYER1_NODE=500
BATCH_SIZE=100
LEARNING_RATE_BASE=0.8
LEARNING_RATE_DECAY=0.99
REGULARIZATION_RATE=0.0001
TRAINING_STEPS=10000
MOVEING_AVEARGE_DECAY=0.99


def inference(input_tensor,avg_class,weights1,biases1,weights2,biases2):
    '''
    定义前向计算的过程:
    avg_class是滑动平均函数，使权重平滑过渡，保留历史数据，
    为None时，表示普通的参数更新过程
    '''
    if avg_class==None:
        layer1=tf.nn.relu(tf.matmul(input_tensor,weights1)+biases1)
        return tf.matmul(layer1,weights2)+biases2
    else:
        layer1=tf.nn.relu(tf.matmul(input_tensor,avg_class.average(weights1)+avg_class.average(biases1)))
        return tf.matmul(layer1,avg_class.average(weights2)+avg_class.average(biases2))

def train(mnist):
    #设置输入变量 placerholder表示占位，开启会话训练的时候需要传入数据
    x=tf.placeholder(tf.float32,[None,INPUT_NODE],name='x-input')
    y_=tf.placeholder(tf.float32,[None,OUTPUT_NODE],name='y-input')

    #设置权重变量，variable表示训练时需要自动更新
    weights1=tf.Variable(tf.random_normal([INPUT_NODE,LAYER1_NODE],stddev=0.1))
    biases1=tf.Variable(tf.constant(0.1,shape=[LAYER1_NODE]))
    weights2=tf.Variable(tf.random_normal([LAYER1_NODE,OUTPUT_NODE],stddev=0.1))
    biases2=tf.Variable(tf.constant(0.1,shape=[OUTPUT_NODE]))
    
    #y=inference(x,None,weights1,biases1,weights2,biases2)
    
    global_step=tf.Variable(0,trainable=False)#不可更新参数
    variable_averages=tf.train.ExponentialMovingAverage(MOVEING_AVEARGE_DECAY,global_step)#min(decay,(1+step)/(10+step)) 后面的变量会越来越大，表示参数的更新越来越稳定，大都依赖于历史数据
    variable_averages_op=variable_averages.apply(tf.trainable_variables())
    average_y=inference(x,variable_averages,weights1,biases1,weights2,biases2)

    cross_entropy=tf.nn.sparse_softmax_cross_entropy_with_logits(logits=average_y,labels=tf.argmax(y_,1))#计算图的输出是每个分类的得分，但是要求输入的标签是正确答案的下标
    cross_entropy_mean=tf.reduce_mean(cross_entropy)

    regularizer=tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    regularization=regularizer(weights1)+regularizer(weights2)
    loss=cross_entropy+regularization

    learning_rate=tf.train.exponential_decay(LEARNING_RATE_BASE,global_step,mnist.train.num_examples/BATCH_SIZE,LEARNING_RATE_DECAY)#学习率成阶梯状衰减 每个epoch衰减一次，也就是一整轮数据训练完衰减一次
    train_step=tf.train.GradientDescentOptimizer(learning_rate).minimize(loss,global_step=global_step)

    train_op=tf.group(train_step,variable_averages_op)#把反向传播是需要更新的参数打包，不使用滑动平均不需要这句话，因为只更新权重。滑动平均还要利用历史数据更新并更新历史数据

    correct_prediction=tf.equal(tf.argmax(average_y,1),tf.argmax(y_,1))
    accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
    

    with tf.Session() as sess:
        tf.global_variables_initializer().run()
        validate_feed={x:mnist.validation.images,y_:mnist.validation.labels}
        test_feed={x:mnist.test.images,y_:mnist.test.labels}

        for i in range(TRAINING_STEPS):
            if i%1000==0:
                validate_acc=sess.run(accuracy,feed_dict=validate_feed)
                print('After %d training steps,validation accuracy using average model is %g' %(i,validate_acc))
                
            xs,ys=mnist.train.next_batch(BATCH_SIZE)
            sess.run(train_op,feed_dict={x:xs,y_:ys})

        test_acc=sess.run(accuracy,feed_dict=test_feed)
        print('After %d training steps,test accuracy using average model is %g' %(TRAINING_STEPS,test_acc))    

def main(argv=None):
    mnist=input_data.read_data_sets("/tmp/data",one_hot=True)
    train(mnist)

if __name__ == '__main__':
    tf.app.run()