基于Tensorflow的CNN简单实现

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/tlzhatao/article/details/70549680

一、概要

基于Tensorflow 1.0+版本实现，利用mnist数据集训练CNN，达到了99.6%的准确率。

二、CNN结构

1.两个卷积层、两个池化层、一个全连接层、一个Dropout层以及一个Softmax层。
2.原始数据为28*28的大小、单通道的图片。
3.第一个卷积层：5*5的卷积核，1个通道，32个不同的卷积核；第一个池化层：2*2的最大池化。
4.第二个卷积层：5*5的卷积核，32个通道，64个不同的卷积核；第二个池化层：2*2的最大池化。
5.全连接层：1024个隐含节点。
6.Droupout层：随机丢弃一部分节点数据避免过拟合。
7.Softmax层：最后的概率输出。

三、实现

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

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

mnist = input_data.read_data_sets('MNIST_data/',one_hot=True)

# print mnist.train.images.shape,mnist.train.labels.shape
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')

train_x = tf.placeholder(tf.float32,[None,784])
train_y = tf.placeholder(tf.float32,[None,10])
x_image = tf.reshape(train_x,[-1,28,28,1])

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)

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)

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(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)

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)

cross_entropy = tf.reduce_mean(-tf.reduce_mean(train_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(train_y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

tf.global_variables_initializer().run()
for i in xrange(20000):
    batch = mnist.train.next_batch(50)
    if i%100 == 0:
        train_accuracy = accuracy.eval(feed_dict={train_x:batch[0],train_y:batch[1],keep_prob:1.0})
        print 'step %d,training accuracy %g' % (i,train_accuracy)
    train_step.run(feed_dict={train_x:batch[0],train_y:batch[1],keep_prob:0.5})

print 'test accuracy %g' % accuracy.eval(feed_dict={train_x:mnist.test.images,train_y:mnist.test.labels,keep_prob:1.0})