炼数成金Tensorflow学习笔记之5.1_改变学习率

代码及分析

# -*- coding: utf-8 -*-
"""
Created on Wed Mar 25 09:07:14 2020

@author: 寒火qwer
"""

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

#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)

#每个批次的大小
batch_size = 100
#计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size

#定义两个placeholder
x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])
keep_prob=tf.placeholder(tf.float32)
# 因为在训练过程中我们想要改变学习率，所以需要将学习率设置成一个变量
lr = tf.Variable(0.001, dtype=tf.float32)

#创建一个简单的神经网络
W1 = tf.Variable(tf.truncated_normal([784,500],stddev=0.1))
b1 = tf.Variable(tf.zeros([500])+0.1)
L1 = tf.nn.tanh(tf.matmul(x,W1)+b1)
L1_drop = tf.nn.dropout(L1,keep_prob) 

W2 = tf.Variable(tf.truncated_normal([500,300],stddev=0.1))
b2 = tf.Variable(tf.zeros([300])+0.1)
L2 = tf.nn.tanh(tf.matmul(L1_drop,W2)+b2)
L2_drop = tf.nn.dropout(L2,keep_prob) 

W3 = tf.Variable(tf.truncated_normal([300,10],stddev=0.1))
b3 = tf.Variable(tf.zeros([10])+0.1)
p = tf.matmul(L2_drop,W3)+b3
prediction = tf.nn.softmax(p)

#交叉熵代价函数
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=p))
#训练
train_step = tf.train.AdamOptimizer(lr).minimize(loss)

#初始化变量
init = tf.global_variables_initializer()

#结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))#argmax返回一维张量中最大的值所在的位置
#求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(51):
        # 在这里，随着训练进程为学习率变量赋不同的值，以达到改变学习率的目的
        sess.run(tf.assign(lr, 0.001 * (0.95 ** epoch)))
        for batch in range(n_batch):
            batch_xs,batch_ys =  mnist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:1.0})
        
        learning_rate = sess.run(lr)
        acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
        print ("Iter " + str(epoch) + ", Testing Accuracy= " + str(acc) + ", Learning Rate= " + str(learning_rate))
'''
Iter 0, Testing Accuracy= 0.9641, Learning Rate= 0.001
Iter 1, Testing Accuracy= 0.9722, Learning Rate= 0.00095
Iter 2, Testing Accuracy= 0.9743, Learning Rate= 0.0009025
Iter 3, Testing Accuracy= 0.9754, Learning Rate= 0.000857375
Iter 4, Testing Accuracy= 0.9766, Learning Rate= 0.000814506
Iter 5, Testing Accuracy= 0.9778, Learning Rate= 0.000773781
Iter 6, Testing Accuracy= 0.9801, Learning Rate= 0.000735092
Iter 7, Testing Accuracy= 0.9811, Learning Rate= 0.000698337
Iter 8, Testing Accuracy= 0.9805, Learning Rate= 0.00066342
Iter 9, Testing Accuracy= 0.9822, Learning Rate= 0.000630249
.....
.....
.....
Iter 46, Testing Accuracy= 0.9834, Learning Rate= 9.44682e-05
Iter 47, Testing Accuracy= 0.9832, Learning Rate= 8.97448e-05
Iter 48, Testing Accuracy= 0.9838, Learning Rate= 8.52576e-05
Iter 49, Testing Accuracy= 0.9832, Learning Rate= 8.09947e-05
Iter 50, Testing Accuracy= 0.9831, Learning Rate= 7.6945e-05
'''