# tensorflow学习序列-MNIST集合上进行分类深度卷积网DCNN

在采用深度卷积网进行MNIST数据集进行分类，准确率达到99.2%左右
import tensorflow as tf
import math
import input_data
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);

def conv2d(x,W):

def max_pool_2x2(x):

# x_training表示训练集合的图像，None表示训练集合的图像的张数不确定，
# 784表示二维图像展为1维向量
# 定义一个po
x_training = tf.placeholder("float",[None,784]);
# 定义一个po
y_training_target = tf.placeholder("float",[None,10]);

# 深度卷积网络的权重和偏置
# 将x_training进行reshape
x_image = tf.reshape(x_training,[-1,28,28,1]);

# 第一层
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);
h_pool1 = max_pool_2x2(h_conv1);

# 第二层
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);
h_pool2 = max_pool_2x2(h_conv2);

# 全连接层
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);
keep_prob = tf.placeholder("float");
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob); # 防止过拟合

# 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); # 深度卷积网输出标签

# 目标函数
cross_entropy = -tf.reduce_sum(y_training_target*tf.log(y_conv))

# 优化方法
# 准确率计算
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_training_target,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess = tf.Session()
sess.run(tf.global_variables_initializer())

for i in range(20000):
batch = mnist.train.next_batch(50)
sess.run(train_step,feed_dict={x_training: batch[0], y_training_target: batch[1], keep_prob: 0.5})
if i%100 == 0:
print("step ",i,"training accuracy", sess.run(accuracy,feed_dict={x_training:batch[0], y_training_target: batch[1], keep_prob: 1.0}))
print("test accuracy",sess.run(accuracy,feed_dict={x_training: mnist.test.images, y_training_target: mnist.test.labels, keep_prob: 1.0}));



#### 深度学习（十五）基于DCNN的人脸特征点定位-CVPR 2013

2016-01-27 11:06:02

#### CNN与句子分类之动态池化方法DCNN--模型介绍篇

2017-03-28 17:44:35

#### 深度学习（十五）基于级联卷积神经网络的人脸特征点定位

2015-11-21 00:08:21

#### CNN与句子分类之动态池化方法DCNN--TensorFlow实现篇

2017-03-29 16:34:29

#### 深度学习 基于DCNN的人脸特征点定位

2017-01-19 17:13:32

#### 基于DCNN的人脸特征点定位-CVPR 2013

2017-06-27 21:02:47

#### 基于DCNN的人脸特征点定位

2017-02-06 16:48:22

#### 卷积神经网络(CNN)在句子建模上的应用

2016-05-19 15:29:36

#### 3D CNN框架结构各层计算

2017-04-29 13:47:20

#### 深度卷积网络CNN与图像语义分割

2015-08-19 22:33:05