tf-Mnist手写字体识别

1.softmax实现

# -*- coding: utf-8 -*-
"""
tensorflow mnist

@author: Administrator
"""
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist=input_data.read_data_sets("MNIST_data/",one_hot=True) #导入数据
sess=tf.InteractiveSession()
x=tf.placeholder(tf.float32,[None,784]) #设置输入特征
w=tf.Variable(tf.zeros([784,10])) #初始化权重
b=tf.Variable(tf.zeros([10])) #初始化偏差

y=tf.nn.softmax(tf.matmul(x,w)+b) #搭建softmax模型 y=wx+b
y_=tf.placeholder(tf.float32,[None,10])
cross_entorpy=tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y),reduction_indices=[1])) #设置损失函数为交叉熵
train_step=tf.train.GradientDescentOptimizer(0.5).minimize(cross_entorpy) #定义梯度下降最小化损失函数

tf.global_variables_initializer().run() #全局初始化
for i in range(1000):
    batch_xs,batch_ys=mnist.train.next_batch(100) #获取batch
    train_step.run({x:batch_xs,y_:batch_ys}) #开始训练

correct_prediction=tf.equal(tf.arg_max(y,1),tf.arg_max(y_,1)) #判断类别

accuray=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
print(accuray.eval({x:mnist.test.images,y_:mnist.test.labels}))

2.带隐含层的神经网络

# -*- coding: utf-8 -*-
"""
Created on Sun May 21 10:36:35 2017

@author: Administrator
"""
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf

mnist=input_data.read_data_sets("MNIST_data/",one_hot=True)
sess=tf.InteractiveSession()
#输入数量
in_units=784
h1_units=300 #隐含层节点数
w1=tf.Variable(tf.truncated_normal([in_units,h1_units],stddev=0.1))#初始化权重，w1截断分布，标准差0.1
b1=tf.Variable(tf.zeros([h1_units])) 
w2=tf.Variable(tf.zeros([h1_units,10]))
b2=tf.Variable(tf.zeros([10]))
#设置输入和drop比率输入
x=tf.placeholder(tf.float32,[None,in_units])
keep_prob=tf.placeholder(tf.float32)

hidden1=tf.nn.relu(tf.matmul(x,w1)+b1) #隐含层激活函数为relu
hidden1_drop=tf.nn.dropout(hidden1,keep_prob) #隐含层drop out
y=tf.nn.softmax(tf.matmul(hidden1_drop,w2)+b2) #输出激活函数为softmax

y_=tf.placeholder(tf.float32,[None,10])
cross_entorpy=tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y),reduction_indices=[1])) #设置损失函数为交叉熵
train_step=tf.train.AdagradOptimizer(0.3).minimize(cross_entorpy) #定义梯度下降最小化损失函数

tf.global_variables_initializer().run() #全局初始化
for i in range(3000):
    batch_xs,batch_ys=mnist.train.next_batch(100) #获取batch
    train_step.run({x:batch_xs,y_:batch_ys,keep_prob:0.75}) #开始训练

correct_prediction=tf.equal(tf.arg_max(y,1),tf.arg_max(y_,1)) #判断类别
accuray=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
print(accuray.eval({x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0}))

3.卷积神经网络

# -*- coding: utf-8 -*-
"""
Created on Thu Sep  8 15:29:48 2016

@author: root
"""
import tensorflow as tf 
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)     #下载并加载mnist数据
x = tf.placeholder(tf.float32, [None, 784])                        #输入的数据占位符
y_actual = tf.placeholder(tf.float32, shape=[None, 10])            #输入的标签占位符

#定义一个函数，用于初始化所有的权值 W
def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)

#定义一个函数，用于初始化所有的偏置项 b
def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)

#定义一个函数，用于构建卷积层
def conv2d(x, W):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

#定义一个函数，用于构建池化层
def max_pool(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')

#构建网络
x_image = tf.reshape(x, [-1,28,28,1])         #转换输入数据shape,以便于用于网络中
W_conv1 = weight_variable([5, 5, 1, 32])      
b_conv1 = bias_variable([32])       
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)     #第一个卷积层
h_pool1 = max_pool(h_conv1)                                  #第一个池化层

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)      #第二个卷积层
h_pool2 = max_pool(h_conv2)                                   #第二个池化层

W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])              #reshape成向量
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)    #第一个全连接层

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

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_predict=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)   #softmax层

cross_entropy = -tf.reduce_sum(y_actual*tf.log(y_predict))     #交叉熵
train_step = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy)    #梯度下降法
correct_prediction = tf.equal(tf.argmax(y_predict,1), tf.argmax(y_actual,1))    
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))                 #精确度计算
sess=tf.InteractiveSession()                          
sess.run(tf.initialize_all_variables())
for i in range(20000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:                  #训练100次，验证一次
    train_acc = accuracy.eval(feed_dict={x:batch[0], y_actual: batch[1], keep_prob: 1.0})
    print('step',i,'training accuracy',train_acc)
    train_step.run(feed_dict={x: batch[0], y_actual: batch[1], keep_prob: 0.5})

test_acc=accuracy.eval(feed_dict={x: mnist.test.images, y_actual: mnist.test.labels, keep_prob: 1.0})
print("test accuracy",test_acc)sh