tensorflow实战（三）实现卷积神经网络

每个卷积层通常进行的步骤：
1.图像通过多个不同的卷积核的滤波，并加bias,提取局部特征，每一个卷积核会映射出一个新的2D图像
2.将前面的卷积核及卷积滤波输出结果，进行非线性的激活函数处理。
3.对激活函数进行池化操作（降采样），一般是最大池化

实验一 Tensorflow 实现简单的卷积神经网络

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

mnist=input_data.read_data_sets("D:/ProgramData/Anaconda3/envs/MNIST_data/",one_hot=True)
in_units = 784 #输入节点数
h1_units = 300 #隐含层节点数
W1 = tf.Variable(tf.truncated_normal([in_units, h1_units], stddev=0.1)) #初始化隐含层权重W1，服从默认均值为0，标准差为0.1的截断正态分布
b1 = tf.Variable(tf.zeros([h1_units])) #隐含层偏置b1全部初始化为0
W2 = tf.Variable(tf.zeros([h1_units, 10])) 
b2 = tf.Variable(tf.zeros([10]))
x = tf.placeholder(tf.float32, [None, in_units])
keep_prob = tf.placeholder(tf.float32) #Dropout失活率

#定义模型结构
hidden1 = tf.nn.relu(tf.matmul(x, W1) + b1)
hidden1_drop = tf.nn.dropout(hidden1, keep_prob)
y = tf.nn.softmax(tf.matmul(hidden1_drop, W2) + b2)

#训练部分
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
train_step = tf.train.AdagradOptimizer(0.3).minimize(cross_entropy)

#定义一个InteractiveSession会话并初始化全部变量
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
correct_prediction = tf.equal(tf.arg_max(y, 1), tf.arg_max(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
for i in range(3001):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    train_step.run({x: batch_xs, y_: batch_ys, keep_prob: 0.75})
    if i % 200 ==0:
		#训练过程每200步在测试集上验证一下准确率，动态显示训练过程
        print(i, 'training_arruracy:', accuracy.eval({x: mnist.test.images, y_: mnist.test.labels, 
                             keep_prob: 1.0}))
print('final_accuracy:', accuracy.eval({x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

实验结果