Python CNN卷积神经网络代码实现

提示：扫一扫查出行
【扫一扫了解最新限行尾号】
复制提示

一.概述

卷积神经网络【Convolutional Neural Networks,CNN】是一类包含卷积计算且具有深度结构的前馈神经网络【Feedforward Neural Networks】是深度学习的代表算法之一。卷积神经网络具有表征学习【representation learning】能力，能够按其阶层结构对输入信息进行平移不变分类。

神经网络实质上是多层函数嵌套形成的数学模型。1998年Yann LeCun等人推出了LeNet-5架构，广泛用于手写字体识别，包含全连接层和sigmoid激活函数，还有卷积层和池化层。

二.代码实现

 # -*- coding: utf-8 -*-

 """

 Created on Wed Nov 21 17:32:28 2018

 @author: zhen

 """

 import tensorflow as tf

 from tensorflow.examples.tutorials.mnist import input_data

 mnist = input_data.read_data_sets('C:/Users/zhen/MNIST_data_bak/', one_hot=True)

 sess = tf.InteractiveSession()

 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):

     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')

 x = tf.placeholder(tf.float32, [None, 784])

 y = tf.placeholder(tf.float32, [None, 10])

 x_image = tf.reshape(x, [-1, 28, 28, 1])

 # 第一层卷积核

 W_conv = weight_variable([5, 5, 1, 16])

 b_conv = bias_variable([16])

 h_conv = tf.nn.relu(conv2d(x_image, W_conv) + b_conv)

 h_pool = max_pool_2x2(h_conv)

 # 第二层卷积核

 W_conv2 = weight_variable([5, 5, 16, 32])

 b_conv2 = bias_variable([32])

 h_conv2 = tf.nn.relu(conv2d(h_pool, W_conv2) + b_conv2)

 h_pool2 = max_pool_2x2(h_conv2)

 # 全连接层

 W_fc = weight_variable([7 * 7 * 32, 512])

 b_fc = bias_variable([512])

 h_pool_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 32])

 h_fc = tf.nn.relu(tf.matmul(h_pool_flat, W_fc) + b_fc)

 # 防止过拟合，使用Dropout层

 keep_prob = tf.placeholder(tf.float32)

 h_fc_drop = tf.nn.dropout(h_fc, keep_prob)

 # Softmax分类

 W_fc2 = weight_variable([512, 10])

 b_fc2 = bias_variable([10])

 y_conv = tf.nn.softmax(tf.matmul(h_fc_drop, W_fc2) + b_fc2)

 # 定义损失函数

 cross_entropy = tf.reduce_mean(-tf.reduce_sum(y * tf.log(y_conv), reduction_indices=[1]))

 train_step = tf.train.AdamOptimizer(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, tf.float32))

 # 训练

 tf.global_variables_initializer().run()

 for i in range(20):

     batch = mnist.train.next_batch(50)

     train_step.run(feed_dict={x:batch[0], y:batch[1], keep_prob:0.5})

 print("test accuracy %g" % accuracy.eval(feed_dict={x:mnist.test.images, y:mnist.test.labels, keep_prob:1.0}))