CNN 理论

我是半路出生的,看的理论方面的博客做个介绍:https://www.cnblogs.com/pinard/p/6483207.html

https://blog.csdn.net/cxmscb/article/details/71023576

 看理论的话第一个博客就够了,第一个博主关于这方面的博客文章我前前后后看了大概十几遍吧,写的很好,能把我这样的渣渣带入门,我想大家也是可以的

实践的话,建议大家去看极客http://wiki.jikexueyuan.com/project/tensorflow-zh/tutorials/mnist_beginners.html

这个是MNIST机器学习入门的代码

"导入数据集"
import  tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot = True)

import  tensorflow as tf
#  "占位符"
x = tf.placeholder(tf.float32,[None, 784])

# 权重和偏置量
W =  tf.Variable(tf.zeros([784, 10 ]))
b = tf.Variable(tf.zeros([10]))

# softmax 模型
y = tf.nn.softmax(tf.matmul(x, W) + b)

# 交叉熵
y_ = tf.placeholder("float",[None, 10])
cross_entropy = -tf.reduce_sum(y_ * tf.log(y))

# 梯度下降算法以0.01的学习速率最小化交叉熵
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
#初始化变量
init = tf.global_variables_initializer()

# 启动模型
sess = tf.Session()
sess.run(init)
for i in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})



correct_prediction = tf.equal(tf.argmax(y, 1),tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))
print(sess.run(accuracy,feed_dict={x: mnist.test.images,y_: mnist.test.labels }))
# 0.9042

  深入MNIST

# -*- coding:utf-8-*-
import  tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data", one_hot = True)

import  tensorflow as tf
sess = tf.InteractiveSession()

x = tf.placeholder("float", shape=[None, 784])
y_ = tf.placeholder("float", shape=[None, 10])

W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

sess.run(tf.global_variables_initializer())

y = tf.nn.softmax(tf.matmul(x, W) + b)
cross_entropy = - tf.reduce_sum(y_ * tf.log(y))

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

for i in range(10000):
    batch = mnist.train.next_batch(90)
    train_step.run(feed_dict= {x: batch[0],y_:batch[1]})

correct_predict = tf.equal(tf.argmax(y,1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_predict,"float"))
print(accuracy.eval(feed_dict={x: mnist.test.images,y_:mnist.test.labels}))
#0.9084   50  1000
#0.9072   60   1000
#0.908   70   1000
#0.9135  80  1000
#0.9151   84 1000
#0.9175  85  1000
#0.9142  86  1000
#0.9133  90  1000
#0.9026 100  1000

#0.098       850  10000
#0.9245      85 10000
#0.924   90 10000

  

 基于mnist的CNN

# -*- coding:utf-8-*-
import  tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data", one_hot = True)

import  tensorflow as tf
sess = tf.InteractiveSession()
x = tf.placeholder("float", shape=[None, 784])
y_ = tf.placeholder("float", shape=[None, 10])

# 权重和偏置量初始化函数
def weight_variable(shape):
    initial = tf.truncated_normal(shape,stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0.1,shape=shape)
    return tf.Variable(initial)

# 卷积和池化
def conv2d(x,W):
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding="SAME")

def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1,2,2,1],strides=[1,2,2,1],padding="SAME")

# 第一层卷积
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
x_image =tf.reshape(x, [-1, 28, 28, 1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

# 第二层卷积
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

# 密集连接层
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)

# dropout
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# 输出层
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))
sess.run(tf.global_variables_initializer())
for i in range(2000):
    batch = mnist.train.next_batch(50)
    if i%100 == 0:
        train_accuracy = accuracy.eval(feed_dict={x: batch[0],y_:batch[1],keep_prob:1.0})
        print("step %d,training accuracy %g "%(i, train_accuracy))
    train_step.run(feed_dict={x: batch[0],y_:batch[1],keep_prob: 0.5})

print("test accuracy %g" % accuracy.eval(feed_dict={x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0}))

  

以上代码都是可以运行的,但是还是建议大家自己去写一次,理解各种函数的意义,将理论和事件结合起来

 

posted @ 2018-04-14 20:02  可以用标点做名字吗  Views(217)  Comments(0Edit  收藏  举报