Tensorflow:MINIST手写体识别

1:设计算法来训练模型
对于处理这种多分类任务,通常用Softmax Regression。工作原理就是对每一种类别估计一个概率,然后取概率最大的类别作为模型的输出结果。
2:定义一个loss function来描述模型对问题的分类精度
对多分类问题通常用cross-entropy作为loss function。loss越小,代表与模型的分类结果与真实值的偏差越小,训练的目的就是不断减小loss,直到达到一个全局最优或局部最优解。
3:定义一个优化算法即可开始训练
采用最常见的随机梯度下降SGD(Stochastic Gradient Descent),定义好后Tensorflow会自动求导并根据反向传播进行训练,在每轮迭代时更新参数来减小loss。
4:全局初始化
5:迭代的执行训练
随机选一部分样本feed给placeholder,称为随机梯度下降。大多数情况下,这比全样本训练的收敛速度快很多。
6:对准确率进行评测
对比预测概率最大的和真实样本类别,相同为true,不同为false。然后由bool值转换为float值再求平均即为准确率。

# -*- 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)
#1定义函数
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')
#2定义输入输出,占位符
x = tf.placeholder("float", shape=[None, 28*28])
y_ = tf.placeholder("float", shape=[None, 10]) 
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(x,[-1,28,28,1])#重置成28*28*1
#3搭建网络,定义算法
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)#28*28*32
h_pool1 = max_pool_2x2(h_conv1)#14*14*32

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)#14*14*64
h_pool2 = max_pool_2x2(h_conv2) #7*7*64

w_fc1 = weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024]) 
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])#重置成1行
f_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,w_fc1)+b_fc1)#1*1*1024
h_fc1_drop = tf.nn.dropout(f_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)#1*1*10
#4优化:用Adam
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) 
#5正确率,初始化所有变量
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess = tf.InteractiveSession()
sess.run(tf.initialize_all_variables())
#6训练
for i in range(2000):  
    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[0:500], y_: mnist.test.labels[0:500], keep_prob: 1.0}))



猜你喜欢

转载自blog.csdn.net/lixiaoyu101/article/details/84326265
今日推荐