DCNN-tensorflow（深度卷积） 以MNIST集合上进行分类为例

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 tfimport mathimport input_datadef 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):    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');mnist = input_data.read_data_sets("MNIST_data/",one_hot=True)# 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pox_training = tf.placeholder("float",[None,784]);# 定义一个poy_training_target = tf.placeholder("float",[None,10]);# 深度卷积网络的权重和偏置# 将x_training进行reshapex_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train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)# 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}));