tf.train.exponential_decay()用法

tf.train.exponential_decay()官网链接

tf.train.exponential_decay(
    learning_rate,
    global_step,
    decay_steps,
    decay_rate,
    staircase=False,
    name=None
)

一句话描述：对学习率learning_rate应用指数衰减。
多说点：固定的学习率总是显得笨拙：太小速度太慢，太大又担心得不到最优解。一个很直接的想法就是随着训练的进行，动态设置学习率——随着训练次数增加，学习率逐步减小。而tf.train.exponential_decay()就是tf内置的一个生成动态减小学习率的函数。
它的公式如下

decayed_learning_rate = learning_rate *
                        decay_rate ^ (global_step / decay_steps)

也即
$decayed\_learning\_rate = learning\_rate*\frac{global\_step}{decay\_step}$
举个例子：
初始学习率LEARNING_RATE_BASE = 0.1
总训练步数GLOBAL_STEPS = 1000
衰减率DECAY_RATE = 0.9
每100步衰减一次(stair=True时)DECAY_STEPS = 100

import tensorflow as tf
import matplotlib.pyplot as plt

LEARNING_RATE_BASE = 0.1
DECAY_RATE = 0.9
GLOBAL_STEPS = 1000
DECAY_STEPS = 100

global_ = tf.Variable(tf.constant(0))
learning_rate_1 = tf.train.exponential_decay(LEARNING_RATE_BASE, global_, DECAY_STEPS, DECAY_RATE, staircase=True)
learning_rate_2 = tf.train.exponential_decay(LEARNING_RATE_BASE, global_, DECAY_STEPS, DECAY_RATE, staircase=False)

LR1 = []
LR2 = []

with tf.Session() as sess:
    for i in range(GLOBAL_STEPS):
        lr1 = sess.run(learning_rate_1, feed_dict={global_: i})
        LR1.append(lr1)
        lr2 = sess.run(learning_rate_2, feed_dict={global_: i})
        LR2.append(lr2)

plt.figure(1)
plt.plot(range(GLOBAL_STEPS), LR2, 'r-')
plt.plot(range(GLOBAL_STEPS), LR1, 'b-')

plt.show()

tf.train.exponential_decay()用法

举一个用tf.train.exponential_decay()优化函数的例子
$loss=(w+1)^2$

#coding:utf-8
#设损失函数 loss=(w+1)^2, 令w初值是常数10。反向传播就是求最优w，即求最小loss对应的w值
#使用指数衰减的学习率，在迭代初期得到较高的下降速度，可以在较小的训练轮数下取得更有收敛度。
import tensorflow as tf

LEARNING_RATE_BASE = 0.1 #最初学习率
LEARNING_RATE_DECAY = 0.99 #学习率衰减率
LEARNING_RATE_STEP = 1  #喂入多少轮BATCH_SIZE后，更新一次学习率，一般设为：总样本数/BATCH_SIZE

#运行了几轮BATCH_SIZE的计数器，初值给0, 设为不被训练
global_step = tf.Variable(0, trainable=False)
#定义指数下降学习率
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,
                                           global_step,
                                           LEARNING_RATE_STEP,
                                           LEARNING_RATE_DECAY,
                                           staircase=True)
#定义待优化参数，初值给10
w = tf.Variable(tf.constant(5, dtype=tf.float32))
#定义损失函数loss
loss = tf.square(w+1)
#定义反向传播方法
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss,
                                                                       global_step=global_step)  # 每运行一次，这里的global_step都+1
#生成会话，训练40轮
with tf.Session() as sess:
    init_op=tf.global_variables_initializer()
    sess.run(init_op)
    for i in range(40):
        sess.run(train_step)
        learning_rate_val = sess.run(learning_rate)
        global_step_val = sess.run(global_step)
        w_val = sess.run(w)
        loss_val = sess.run(loss)
        print ("After %s steps: global_step is %f, w is %f, learning rate is %f, loss is %f" % (i, global_step_val, w_val, learning_rate_val, loss_val))

tf.train.exponential_decay()用法

相关推荐