代码:tf.nn.tanh(a)
功能:逐元素应用Tanh函数(双曲正切)对数据进行激活,将元素调整到区间(-1,1)内
函数:
T
a
n
h
(
x
)
=
e
x
−
e
−
x
e
x
+
e
−
x
Tanh(x)=\frac{e^x-e^{-x}}{e^x+e^{-x}}
Tanh(x)=ex+e−xex−e−x
参考代码如下:
import tensorflow as tf
import numpy as np
a = tf.constant([1.7, -0.5, 8.4, -2.1, 0.5, -6.5], dtype = tf.float32)
b = tf.nn.tanh(a)
with tf.Session() as sess:
print('Input type:', a)
print('Input:', sess.run(a))
print('Return type:', b)
print('Output:', sess.run(b))
输出如下:
Input type: Tensor(“Const:0”, shape=(6,), dtype=float32)
Input: [ 1.7 -0.5 8.4 -2.1 0.5 -6.5]
Return type: Tensor(“Tanh:0”, shape=(6,), dtype=float32)
Output: [ 0.935409 -0.46211717 0.9999999 -0.970452 0.46211717 -0.99999547]