Python | Tensorflow atanh () method

The tensorflow.math module provides support for many basic mathematical operations. The tf.atanh () [alias tf.math.atanh ] function provides support for the inverse hyperbolic tangent function in Tensorflow … Its domain is in the range [-1, 1] and it returns nan for any entry outside this range. Input type — tensor, and if the input contains more than one element, the elementwise inverse hyperbolic tangent is calculated.

Syntax : tf.atanh (x, name = None) or tf.math. atanh (x, name = None)

Parameters :
x : A tensor of any of the following types: float16, float32, float64, complex64, or complex128.
name (optional): The name for the operation.

Return type : A tensor with the same type as that of x.

Code # 1:

# Library import Tensorflow

import tensorflow as tf

 
# Constant vector of size 6

a = tf.constant ([ 1.0 , - 0.5 , - 1 , 2.4 , 0.0 , - 6.5 ], dtype = tf.float32)

 
# Using the atanh function and
# saving the result to & # 39; b & # 39;

b = tf.atanh (a, name = `atanh` )

 
< code class = "comments"> # Initiating a Tensorflow session
with tf.Session () as sess:

print ( `Input type:` , a)

print ( `Input:` , sess.run (a))

print ( `Return type:` , b)

print ( `Output:` , sess .run (b))

Exit:

 Input type: Tensor ("Const_3: 0", shape = (6,), dtype = f loat32) Input: [1. -0.5 -1. 2.4 0. -6.5] Return type: Tensor ("atanh_1: 0", shape = (6,), dtype = float32) Output: [inf -0.54930615 -inf nan 0. nan] 

Code # 2: Rendering

# Import Tensorflow library

import tensorflow as tf

 
# Import NumPy library

import numpy as np

 
# Import matplotlib.pylot function

import matplotlib.pyplot as plt

 
# Vector size 15 with values ​​from -1 to 1

a = np.linspace ( - 1 , 1 , 15 )

 
# Applying inverse hyperbolic tangent
# function and saving the result to & # 39; b & # 39;

b = tf.atanh (a, name = `atanh` )

  
# Initiating a Tensorflow session
with tf.Session () as sess:

print ( `Input: ` , a)

  print ( `Output:` , sess.run (b))

plt.plot (a, sess.run (b), color = `red` , marker = "o"

  plt.title ( "tensorflow.atanh"

plt.xlabel ( "X"

plt.ylabel ( "Y"

  

  plt.show ()

Output :

 Input: [-1. -0.85714286 -0.71428571 -0.57142857 -0.42857143 -0.28571429 -0.14285714 0. 0.14285714 0.28571429 0.42857143 0.57142857 0.71428571 0.85714286 1.] Output: [-inf -1.28247468 -0.89587973 -0.64964149 -0.45814537 -0.29389333 -0.14384104 0. 0.14384104 0.29389333 0.45814537 0.64964149 0.89587973 1.28247468 inf]