MNIST识别数字(TensorFlow框架)

最新推荐文章于 2024-05-21 14:45:00 发布

原创最新推荐文章于 2024-05-21 14:45:00 发布 · 932 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#TensorFlow #MNIST #手写数字识别

python 同时被 2 个专栏收录

29 篇文章

订阅专栏

深度学习

12 篇文章

订阅专栏

本文介绍了一种使用TensorFlow实现的手写数字识别方法，在MNIST数据集上达到了98.4%的准确率。该模型采用单层全连接神经网络，并通过随机梯度下降进行参数优化。

本篇文章主要实现在TensorFlow平台下识别MNIST数据集上的0-9十个数字，通过随机梯度下降算法优化参数，准确率在30000次迭代后保持在98.4%。

下面是完整的代码：

'''MNIST数字识别问题'''
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

INPUT_NODE = 784   #输入层节点数
OUTPUT_NODE = 10   #输出层节点数

LAYER1_NODE = 500   #隐藏层节点数 
BATCH_SIZE = 100   #一个batch中训练数据的个数 
LEARNING_RATE_BASE = 0.8  #初始学习率 
LEARNING_RATE_DECAY = 0.99  #学习率的衰减率 
REGULARIZATION_RATE = 0.0001  #描述模型复杂度的正则化在损失函数中的系数 
TRAINING_STEPS = 30000       #训练轮数 
MOVING_AVERAGE_DECAY = 0.99   #滑动平均衰减率 

'''计算神经网络的前向传播结果'''
def inference(input_tensor,avg_class,weights1,biases1,weights2,biases2):
    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)

'''训练模型的过程'''
def train(mnist):
    x = tf.placeholder(tf.float32,[None,INPUT_NODE],name='x-input')
    y_ = tf.placeholder(tf.float32,[None,OUTPUT_NODE],name='y-input')

    weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE,LAYER1_NODE],stddev=0.1))
    biases1 = tf.Variable(tf.constant(0.1,shape=[LAYER1_NODE]))
    weights2 = tf.Variable(tf.truncated_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)

    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY,global_step)
 
    variable_averages_op = variable_averages.apply(tf.trainable_variables())
     
    average_y = inference(x,variable_averages,weights1,biases1,weights2,biases2)
    
    '''计算交叉謪'''
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(y_,1),logits=y)
    cross_entropy_mean = tf.reduce_mean(cross_entropy)
    
    '''计算L2正则化损失函数'''
    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    regularization = regularizer(weights1) + regularizer(weights2)
    loss = cross_entropy_mean + regularization  #损失函数等于两部分相加
    learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,global_step,mnist.train.num_examples/BATCH_SIZE,LEARNING_RATE_DECAY)

    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss,global_step=global_step)
    train_op = tf.group(train_step,variable_averages_op)
    
    correct_prediction = tf.equal(tf.argmax(average_y,1),tf.argmax(y_,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

    '''初始化会话并开始训练过程'''
    with tf.Session() as sess:
        #tf.initialize_all_variables().run()
        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 step(s),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 step(s),test accuracy using average ""model is %g" % (TRAINING_STEPS,test_acc))

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

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

运行结果：