tensorflow学习笔记（1）

使用tensorflow实现一个简单的卷积网络，使用数据集MNIST，预测可以达到99.2%的准确率。卷积网络由两个卷积层加一个全连接层构成。
#-*- coding: utf-8 -*-
"""
Spyder Editor
This is a temporary script file.
"""

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

#载入MNIST数据集，并创建默认的Interactive Session
mnist=input_data.read_data_sets("MNIST_data/",one_hot=True)
sess = tf.InteractiveSession()

`#定义初始化函数 给权重加入噪音
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)

#卷积层与池化层

def conv2d(x, W):
#x 是输入 W是卷积的参数 ：【5，5，1，32】代表5*5的卷积大小
#1表示chaanel 32表示卷积核数量
#strides表示移动步长【1，1，1，1】表示不遗漏每一个点 padding:same 加上边界
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])

#定义第一个卷积层
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)

#定义第二个卷积层
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)

#两次最大池化，28*28变成7*7，7*7*64转化为1d向量
W_fc1 = weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024])
h_pool2_float = tf.reshape(h_pool2, [-1,7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_float, W_fc1)+b_fc1)

#加入dropout防止过拟合
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)

#最后一层输出连接一个softmax 得到概率输出
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)

#定义损失函数 cross entropy 优化器：adam
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)

#定义评估准确率的函数
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

#开始训练，初始化所有参数，drop=0.5 用50的mini-batch 进行20000次迭代，共100w样本，100次评估一次

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}))