一、学习内容：
1.搭建卷积神经网络
2.Saver 保存与读取
二、代码及注释：
1.搭建卷积神经网络
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
def compute_accuracy(v_xs,v_ys):
global prediction # 将prediction定义成全局变量
y_pre = sess.run(prediction,feed_dict={
xs:v_xs,keep_prob:1}) # 将xs赋值给prediction生成预测值
correct_prediction = tf.equal(tf.argmax(y_pre,1),tf.argmax(v_ys,1)) # 对比和真实数据的差别
# tf.argmax用来返回最大值所在的下标，0表示按列比较返回，1表示按行比较返回
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
result = sess.run(accuracy,feed_dict={
xs:v_xs,ys:v_ys,keep_prob:1}) # 这里的result是一个百分比
return result
# weights
def weight_variable(shape):
inital = tf.truncated_normal(shape,stddev=0.1)
return tf.Variable(inital)
# biases
def bias_variable(shape):
inital = tf.constant(0.1,shape=shape)
return tf.Variable(inital)
# 定义二维卷积函数
def cov2d(x,W): # x输入的值，图片的所有参数 W是卷积层的权重
# stride [1,x_movement,y_movement,1]
# must hace strides[0] = strides[3] = 1
return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
#定义步长[1,1,1,1]，第一个和最后一个是默认值
#中间两个1代表padding时在x方向运动一步，y方向运动一步，padding采用的方式是SAME。
def max_pool_2x2(x):
return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
# SAME的padding方式，输出图片的大小没有变化依然，只是厚度变厚
# define placeholder for input to network
xs = tf.placeholder(tf.float32,[None,784])
ys = tf.placeholder(tf.float32,[None,10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs,[-1,28,28,1]) # -1代表暂时不指定图片的维度 28*28个像素点 1是channel的数量，黑白
#printf(x_image.shape) # [n_samples,28,28,1]
## conv1 layer ##
W_conv1 = weight_variable([5,5,1,32]) # 卷积核patch大小为5x5, insize 1(image的厚度),输出32像素
b_covn1 = bias_variable([32])
h_conv1 = tf.nn.relu(cov2d(x_image,W_conv1) + b_covn1) # 激活函数relu非线性化处理 outputsize:28x28x32
h_pool1 = max_pool_2x2(h_conv1) # outputsize: 14x14x32
## conv2 layer ##
W_conv2 = weight_variable([5,5,32,64]) # patch 5x5,insize 32(image的厚度),outsize 64
b_covn2 = bias_variable([64])
h_conv2 = tf.nn.relu(cov2d(h_pool1,W_conv2) + b_covn2) # relu非线性化处理 outputsize:14x14x32
h_pool2 = max_pool_2x2(h_conv2) # outputsize: 7x7x32
## func1 layer 全连接层##
W_fc1 = weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])
# 将三维数据变成一维 [n_samples,7,7,64]->>[n_sample,7*7*64]
# -1表示先不考虑输入图片例子维度, 将上一个输出结果展平
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob) #防止过拟合
## func2 layer ##
W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2) #使用softmax进行分类处理
## the error between prediction and real data ##
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for i in range(1000):
batch_xs,batch_ys = mnist.train.next_batch(100)
sess.run(train_step,feed_dict={
xs:batch_xs,ys:batch_ys,keep_prob:0.5})
if i % 50 ==0:
print(compute_accuracy(mnist.test.images,mnist.test.labels))
2.Saver保存读取
from __future__ import print_function
import tensorflow as tf
import numpy as np
# # Save to file
# W = tf.Variable([[1,2,3],[3,4,5]], dtype=tf.float32, name='weights')
# b = tf.Variable([[1,2,3]], dtype=tf.float32, name='biases')
#
# init = tf.initialize_all_variables()
# saver = tf.train.Saver() # 使用saver来存储各种变量
#
# with tf.Session() as sess:
# sess.run(init)
# save_path = saver.save(sess, "my_net/save_net.ckpt")
# print("Save to path: ", save_path)
###################################################################################
# restore variables
# redefine the same shape and same type for your variables 只有shape和type完全一样才能正确导入
W = tf.Variable(np.arange(6).reshape((2, 3)), dtype=tf.float32, name="weights")
b = tf.Variable(np.arange(3).reshape((1, 3)), dtype=tf.float32, name="biases")
# not need init step 不需要初始化操作
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, "my_net/save_net.ckpt")
print("weights:", sess.run(W))
print("biases:", sess.run(b))