tensorflow实战之 简单卷积神经网络

# -*- coding: utf-8 -*-
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets('MNIST_data/',one_hot = True )
sess = tf.InteractiveSession() # 后面可以直接对Session进行操作，不必sess.run


def weight_variable(shape):   #  输入矩阵的尺寸，返回weight矩阵
    initial = tf.truncated_normal(shape,stddev = 0.1) # 初始化的变量为截断的正态分布标准差为0.1
    return tf.Variable(initial) # 用tf.Variable生成变量


def bias_variable(shape): # 根据输入矩阵， 返回初始的偏置向量， 偏置常数为0.1
    initial = tf.constant(0.1,shape = shape ) # 用tf.constant生成该维度的常数矩阵
    return tf.Variable(initial) 
def conv2d(x, w):  # 输入两个矩阵返回其卷积结果
    return tf.nn.conv2d(x,w, strides = [1,1,1,1], padding = 'SAME') # 用tf.nn.conv2d计算卷积


def max_pool_2x2(x): #池化函数 其中参数ksize为核函数的大小， strides 是移动步长，
#padiing参数有两个可选值其中same是去除两端相同值，valid是去除最右端
    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_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax( y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))


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