https://blog.csdn.net/u013061183/article/details/79334697
#!/usr/bin/env python3
# -*- coding: utf-8 -*- '''
学习率较大容易搜索震荡(在最优值附近徘徊),学习率较小则收敛速度较慢,
那么可以通过初始定义一个较大的学习率,通过设置decay_rate来缩小学习率,减少迭代次数。
tf.train.exponential_decay就是用来实现这个功能。
'''
__author__ = 'Zhang Shuai'
import tensorflow as tf
import matplotlib.pyplot as plt
learning_rate = 0.1 # 学习速率
decay_rate = 0.96 # 衰减速率,即每一次学习都衰减为原来的0.96
global_steps = 1000 # 总学习次数
# 如果staircase为True,那么每decay_steps改变一次learning_rate,
# 改变为learning_rate*(decay_rate**decay_steps)
# 如果为False则,每一步都改变,为learning_rate*decay_rate
decay_steps = 100
global_ = tf.placeholder(dtype=tf.int32)
# 如果staircase=True,那么每decay_steps更新一次decay_rate,如果是False那么每一步都更新一次decay_rate。
c = tf.train.exponential_decay(learning_rate, global_, decay_steps, decay_rate, staircase=True)
d = tf.train.exponential_decay(learning_rate, global_, decay_steps, decay_rate, staircase=False)
T_C = []
F_D = []
with tf.Session() as sess:
for i in range(global_steps):
T_c = sess.run(c, feed_dict={global_: i})
T_C.append(T_c)
F_d = sess.run(d, feed_dict={global_: i})
F_D.append(F_d)
plt.figure(1)
l1, = plt.plot(range(global_steps), F_D, 'r-') # staircase=False
l2, = plt.plot(range(global_steps), T_C, 'b-') # staircase=True
plt.legend(handles=[l1, l2, ], labels=['staircase=False', 'staircase=True'], loc='best', )
plt.show()
结果如图:
---------------------
原文:https://blog.csdn.net/u013061183/article/details/79334697