TensorFlow学习之实现深度卷积分类器

1 利用TensorFlow在MNIST数据上构建深度卷积分类器
  数据集：MNIST 数据,MNIST是一个入门级的计算机视觉数据集，包含各种手写体数字图片
本文分为两部分（1）softmax模型实现
                            （2）深度卷积分类器实现
2 实验代码及结果截图
#coding:utf-8
#softmax模型

#下载数据
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
import tensorflow as tf
#创建计算图
sess=tf.InteractiveSession()
#创建计算图的输入和输出
x=tf.placeholder("float",shape=[None,784])#784是指单张展开的MNISt图片的维度数
y_=tf.placeholder("float",shape=[None,10])
#为模型定义权重和偏置
w=tf.Variable(tf.zeros([784,10]))
b=tf.Variable(tf.zeros([10]))
sess.run(tf.initialize_all_variables())
#预测分类和损失函数
y=tf.nn.softmax(tf.matmul(x,w)+b)
#最小化损失函数
cross_entropy=-tf.reduce_sum(y_*tf.log(y))
#训练模型
train_step=tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
for i in range(1000):
    batch=mnist.train.next_batch(50)
    train_step.run(feed_dict={x:batch[0],y_:batch[1]})
correct_prediction=tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,"float"))
print "test accuracy:", accuracy.eval(feed_dict={x:mnist.test.images,y_:mnist.test.labels})



#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)
#减少过拟合
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)
#训练和评估模型
cross_entropy=-tf.reduce_sum(y_*tf.log(y_conv))
train_step=tf.train.AdadeltaOptimizer(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.initialize_all_variables())
for i in range(20000):
    batch=mnist.train.next_batch(50)
    if i%100==0:
        train_accurcy=accuracy.eval(feed_dict={x:batch[0],y_:batch[1],keep_prob:1.0})
        print  "step:",i,"train_accurcy:",train_accurcy
    train_step.run(feed_dict={x:batch[0],y_:batch[1],keep_prob:0.5})
print "test accuracy:",accuracy.eval(feed_dict={x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0})





运行的结果就不所有都截图了，温馨提示：后面的程序运行起来会很慢很慢，需要将近半个小时才可以完成；
3  从两次的结果可以看出，准确性明显增加