tensorflow使用神经网络实现mnist分类
作者:Missayaa 时间:2023-07-05 10:19:13
本文实例为大家分享了tensorflow神经网络实现mnist分类的具体代码,供大家参考,具体内容如下
只有两层的神经网络,直接上代码
#引入包
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#引入input_data文件
from tensorflow.examples.tutorials.mnist import input_data
#读取文件
mnist = input_data.read_data_sets('F:/mnist/data/',one_hot=True)
#定义第一个隐藏层和第二个隐藏层,输入层输出层
n_hidden_1 = 256
n_hidden_2 = 128
n_input = 784
n_classes = 10
#由于不知道输入图片个数,所以用placeholder
x = tf.placeholder("float",[None,n_input])
y = tf.placeholder("float",[None,n_classes])
stddev = 0.1
#定义权重
weights = {
'w1':tf.Variable(tf.random_normal([n_input,n_hidden_1],stddev = stddev)),
'w2':tf.Variable(tf.random_normal([n_hidden_1,n_hidden_2],stddev=stddev)),
'out':tf.Variable(tf.random_normal([n_hidden_2,n_classes],stddev=stddev))
}
#定义偏置
biases = {
'b1':tf.Variable(tf.random_normal([n_hidden_1])),
'b2':tf.Variable(tf.random_normal([n_hidden_2])),
'out':tf.Variable(tf.random_normal([n_classes])),
}
print("Network is Ready")
#前向传播
def multilayer_perceptrin(_X,_weights,_biases):
layer1 = tf.nn.sigmoid(tf.add(tf.matmul(_X,_weights['w1']),_biases['b1']))
layer2 = tf.nn.sigmoid(tf.add(tf.matmul(layer1,_weights['w2']),_biases['b2']))
return (tf.matmul(layer2,_weights['out'])+_biases['out'])
#定义优化函数,精准度等
pred = multilayer_perceptrin(x,weights,biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = pred,labels=y))
optm = tf.train.GradientDescentOptimizer(learning_rate = 0.001).minimize(cost)
corr = tf.equal(tf.argmax(pred,1),tf.argmax(y,1))
accr = tf.reduce_mean(tf.cast(corr,"float"))
print("Functions is ready")
#定义超参数
training_epochs = 80
batch_size = 200
display_step = 4
#会话开始
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
#优化
for epoch in range(training_epochs):
avg_cost=0.
total_batch = int(mnist.train.num_examples/batch_size)
for i in range(total_batch):
batch_xs,batch_ys = mnist.train.next_batch(batch_size)
feeds = {x:batch_xs,y:batch_ys}
sess.run(optm,feed_dict = feeds)
avg_cost += sess.run(cost,feed_dict=feeds)
avg_cost = avg_cost/total_batch
if (epoch+1) % display_step ==0:
print("Epoch:%03d/%03d cost:%.9f"%(epoch,training_epochs,avg_cost))
feeds = {x:batch_xs,y:batch_ys}
train_acc = sess.run(accr,feed_dict = feeds)
print("Train accuracy:%.3f"%(train_acc))
feeds = {x:mnist.test.images,y:mnist.test.labels}
test_acc = sess.run(accr,feed_dict = feeds)
print("Test accuracy:%.3f"%(test_acc))
print("Optimization Finished")
程序部分运行结果如下:
Train accuracy:0.605
Test accuracy:0.633
Epoch:071/080 cost:1.810029302
Train accuracy:0.600
Test accuracy:0.645
Epoch:075/080 cost:1.761531130
Train accuracy:0.690
Test accuracy:0.649
Epoch:079/080 cost:1.711757494
Train accuracy:0.640
Test accuracy:0.660
Optimization Finished
来源:https://blog.csdn.net/Missayaaa/article/details/80065319
标签:tensorflow,神经网络,mnist分类
0
投稿
猜你喜欢
asp连接MYSQL数据库的连接字符串(参数OPTION)
2009-03-09 18:24:00
防止表格或或div层被撑开的几种方法
2008-01-01 15:33:00
SQL Server数据迁移至云端应用技巧谈
2011-05-05 08:01:00
CCTV视频里的全屏播放功能实现
2023-06-24 18:39:29
MSAgent 详细解说
2023-07-03 14:07:45
利用sys.sysprocesses检查SqlServer的阻塞和死锁
2011-11-03 17:24:11
Oracle数据库逻辑备份的SH文件
2010-07-27 13:26:00
傲游对开发人员的影响越来越大了
2009-10-14 13:16:00
php面向对象程序设计
2023-05-29 15:55:45
CSS盒模型
2009-06-09 14:23:00
MS SQL 查询数据在数据库中所在行
2009-04-26 19:36:00
JavaScript版的DateAdd、DateDiff、IsDate函数
2008-01-30 15:35:00
一个可应用在ASP 标记加密文件的MD5的DLL组件
2008-04-12 07:21:00
Google的用户体验设计原则
2009-01-12 18:31:00
AJAX简单应用实例-弹出层
2011-04-14 10:55:00
Oracle 8i在P4上的安装
2010-07-31 13:19:00
搞定web设计中网页路径问题
2007-09-22 08:52:00
sql2005与sql200数据导入导出
2009-03-13 13:16:00
编程经验点滴 动态SQL的拼接技巧
2012-11-30 20:03:58
捕捉并保存ASP运行错误的函数代码
2012-11-30 20:24:43