tensorflow CNN

卷积神经网络需要创建很多的权重和偏置，所以定义函数来重复调用。

tf.nn.conv2d(x,w,strides=[1,1,1,1],padding=‘SAME’)

x是输入，w是卷积的参数。w=[5,5,1,32]，5*5是卷积核的尺寸，1代表通道数（灰度是1，彩色RGB是3），32代表有32个卷积核数量。strides,表示移动步长，1为不遗漏图上的每一个点。padding='SAME’表示卷积的输入和输出保持相同的尺寸。

tf.nn.max_pool(x,ksize=[1,2,2,1],strides[1,2,2,1], padding=‘SAME’)

22的最大池化即22降为1*1。横竖为2，strides与ksize保持同步。

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

-1指样本的数量不固定，28*28=784,1表示颜色通道数。

其中N是输入图像的size，F是filter的size，stride是滑动的步长。输出大小为(N-F)/stride+1。当N=7,F=3，stride=3时，(N-F)/stride+1=2.33 发现出现了不能整除的现象。这就需要padding！！！(N-F+2 * padding)/stride+1，当padding=1时，（7-3+2*1）/3+1=3。同理池化操作。

注意这里使用了padding=‘SAME’ 所以出来的尺寸是28/2/2=7 7 * 7的大小，不然则是4 * 4.

import numpy as np
import sklearn.preprocessing as prep
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

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

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])

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_sum(y_*tf.log(y_conv),
                                            reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_pre=tf.equal(tf.argmax(y_,1),tf.argmax(y_conv,1))
accuracy=tf.reduce_mean(tf.cast(correct_pre,tf.float32))
init=tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    for i in range(20000):
        batch_xs, batch_ys=mnist.train.next_batch(50)
        if i%200==0:
            print('Train accuracy:',accuracy.eval({x:batch_xs,y_:batch_ys,
                                             keep_prob:1.0}))
            continue
        _,loss=sess.run([train_step,cross_entropy],feed_dict=
                        {x:batch_xs,y_:batch_ys,keep_prob:0.75})



    print('Test accuracy:',accuracy.eval({x:mnist.test.images,y_:mnist.test.labels,
                                     keep_prob:1.0}))