TensorFlow神经网络中Dropout层

最新推荐文章于 2023-11-26 19:22:46 发布

原创最新推荐文章于 2023-11-26 19:22:46 发布 · 1.3k 阅读

5 ·

CC 4.0 BY-SA版权

本文介绍了一个基于TensorFlow的深度神经网络模型在MNIST手写数字数据集上的实现过程。通过构建包含多层全连接层的神经网络，并采用dropout技术防止过拟合，实现了对MNIST数据集的有效分类，最终达到较高的训练和测试准确率。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

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

#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)

#每个批次的大小
batch_size = 100
#计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size

#定义两个placeholder
x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])
keep_prob=tf.placeholder(tf.float32)

#创建一个简单的神经网络
W1 = tf.Variable(tf.truncated_normal([784,2000],stddev=0.1))
b1 = tf.Variable(tf.zeros([2000])+0.1)
L1 = tf.nn.tanh(tf.matmul(x,W1)+b1)
L1_drop = tf.nn.dropout(L1,keep_prob) 

W2 = tf.Variable(tf.truncated_normal([2000,2000],stddev=0.1))
b2 = tf.Variable(tf.zeros([2000])+0.1)
L2 = tf.nn.tanh(tf.matmul(L1_drop,W2)+b2)
L2_drop = tf.nn.dropout(L2,keep_prob) 

W3 = tf.Variable(tf.truncated_normal([2000,1000],stddev=0.1))
b3 = tf.Variable(tf.zeros([1000])+0.1)
L3 = tf.nn.tanh(tf.matmul(L2_drop,W3)+b3)
L3_drop = tf.nn.dropout(L3,keep_prob) 

W4 = tf.Variable(tf.truncated_normal([1000,10],stddev=0.1))
b4 = tf.Variable(tf.zeros([10])+0.1)
prediction = tf.nn.softmax(tf.matmul(L3_drop,W4)+b4)

#二次代价函数
# loss = tf.reduce_mean(tf.square(y-prediction))
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
#使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
#train_step = tf.train.AdamOptimizer(1e-2).minimize(loss)
#初始化变量
init = tf.global_variables_initializer()

#结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))#argmax返回一维张量中最大的值所在的位置
#求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(31):
        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})
        train_acc = sess.run(accuracy,feed_dict={x:mnist.train.images,y:mnist.train.labels,keep_prob:1.0})
        print("Iter " + str(epoch) + ",Testing Accuracy " + str(test_acc) +",Training Accuracy " + str(train_acc))

结果如下：

Iter 0,Testing Accuracy 0.9182,Training Accuracy 0.9096182
Iter 1,Testing Accuracy 0.9315,Training Accuracy 0.9265818
Iter 2,Testing Accuracy 0.9366,Training Accuracy 0.9344909
Iter 3,Testing Accuracy 0.9419,Training Accuracy 0.94174546
Iter 4,Testing Accuracy 0.9447,Training Accuracy 0.9445818
Iter 5,Testing Accuracy 0.946,Training Accuracy 0.9479455
Iter 6,Testing Accuracy 0.9462,Training Accuracy 0.95083636
Iter 7,Testing Accuracy 0.9499,Training Accuracy 0.95336366
Iter 8,Testing Accuracy 0.9545,Training Accuracy 0.95705456
Iter 9,Testing Accuracy 0.9555,Training Accuracy 0.95863634
Iter 10,Testing Accuracy 0.9566,Training Accuracy 0.96065456
Iter 11,Testing Accuracy 0.9576,Training Accuracy 0.9611273
Iter 12,Testing Accuracy 0.9592,Training Accuracy 0.96352726
Iter 13,Testing Accuracy 0.9592,Training Accuracy 0.9640909
Iter 14,Testing Accuracy 0.9598,Training Accuracy 0.9655455
Iter 15,Testing Accuracy 0.9631,Training Accuracy 0.96729094
Iter 16,Testing Accuracy 0.9628,Training Accuracy 0.96827275
Iter 17,Testing Accuracy 0.9629,Training Accuracy 0.96885455
Iter 18,Testing Accuracy 0.9658,Training Accuracy 0.96956366
Iter 19,Testing Accuracy 0.9663,Training Accuracy 0.9702
Iter 20,Testing Accuracy 0.9673,Training Accuracy 0.9715818
Iter 21,Testing Accuracy 0.967,Training Accuracy 0.97187275
Iter 22,Testing Accuracy 0.9675,Training Accuracy 0.9728364
Iter 23,Testing Accuracy 0.9684,Training Accuracy 0.9733091
Iter 24,Testing Accuracy 0.9677,Training Accuracy 0.9745273
Iter 25,Testing Accuracy 0.9689,Training Accuracy 0.9752909
Iter 26,Testing Accuracy 0.9699,Training Accuracy 0.97547275
Iter 27,Testing Accuracy 0.9701,Training Accuracy 0.9766727
Iter 28,Testing Accuracy 0.969,Training Accuracy 0.97685456
Iter 29,Testing Accuracy 0.97,Training Accuracy 0.9769818
Iter 30,Testing Accuracy 0.9697,Training Accuracy 0.9770727