【Tensorflow】设置自动衰减的学习率

在训练神经网络的过程中,合理的设置学习率是一个非常重要的事情。对于训练一开始的时候,设置一个大的学习率,可以快速进行迭代,在训练后期,设置小的学习率有利于模型收敛和稳定性。

tf.train.exponential_decay(learing_rate, global_step, decay_steps, decay_rate, staircase=False)

  • learning_rate:学习率
  • global_step:全局的迭代次数
  • decay_steps:进行一次衰减的步数
  • decay_rate:衰减率
  • staircase:默认为False,如果设置为True,在修改学习率的时候会进行取整

转换方程:

d e c a y e d _ l e a r n i n g _ r a t e = l e a r n i n g _ r a t e d e c a y _ r a t e g l o b a l _ s t e p d e c a y _ s t e p s

实例:

import tensorflow as tf
import matplotlib.pyplot as plt

start_learning_rate = 0.1
decay_rate = 0.96
decay_step = 100
global_steps = 3000

_GLOBAL = tf.Variable(tf.constant(0))
S = tf.train.exponential_decay(start_learning_rate, _GLOBAL, decay_step, decay_rate, staircase=True)
NS = tf.train.exponential_decay(start_learning_rate, _GLOBAL, decay_step, decay_rate, staircase=False)

S_learning_rate = []
NS_learning_rate = []

with tf.Session() as sess:
    for i in range(global_steps):
        print(i, ' is training...')
        S_learning_rate.append(sess.run(S, feed_dict={_GLOBAL: i}))
        NS_learning_rate.append(sess.run(NS, feed_dict={_GLOBAL: i}))

plt.figure(1)
l1, = plt.plot(range(global_steps), S_learning_rate, 'r-')
l2, = plt.plot(range(global_steps), NS_learning_rate, 'b-')
plt.legend(handles=[l1, l2, ], labels=['staircase', 'no-staircase'], loc='best')
plt.show()

该实例表示训练过程总共迭代3000次,每经过100次,就会对学习率衰减为原来的0.96。

效果图:
这里写图片描述

参考链接:
1.https://www.tensorflow.org/api_docs/python/tf/train/exponential_decay
2.https://blog.csdn.net/UESTC_C2_403/article/details/72213286

猜你喜欢

转载自blog.csdn.net/twt520ly/article/details/80402803