Python | Tensorflow asinh() method
Tensorflow is an open-source machine learning library developed by Google. One of its applications is to develop deep neural networks.
The module tensorflow.math
provides support for many basic mathematical operations. Function tf.asinh()
[alias tf.math.asinh
] provides support for the inverse hyperbolic sine function in Tensorflow. The input type is tensor and if the input contains more than one element, element-wise inverse hyperbolic sine is computed.
Syntax: tf.asinh(x, name=None) or tf.math.asinh(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:
Python3
import tensorflow as tf
a = tf.constant([ 1.0 , - 0.5 , 3.4 , 22.1 , 0.0 , - 6.5 ],
dtype = tf.float32)
b = tf.asinh(a, name = 'asinh' )
with tf.Session() as sess:
print ( 'Input type:' , a)
print ( 'Input:' , sess.run(a))
print ( 'Return type:' , b)
print ( 'Output:' , sess.run(b))
|
Output:
Input type: Tensor("Const_1:0", shape=(6, ), dtype=float32)
Input: [ 1. -0.5 3.4 22.1 0. -6.5]
Return type: Tensor("asinh:0", shape=(6, ), dtype=float32)
Output: [ 0.8813736 -0.48121184 1.9378793 3.7892363 0. -2.5708146 ]
Code #2: Visualization
Python3
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
a = np.linspace( - 10 , 10 , 15 )
b = tf.asinh(a, name = 'asinh' )
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.asinh" )
plt.xlabel( "X" )
plt.ylabel( "Y" )
plt.show()
|
Output:
Input: [-10. -8.57142857 -7.14285714 -5.71428571 -4.28571429
-2.85714286 -1.42857143 0. 1.42857143 2.85714286
4.28571429 5.71428571 7.14285714 8.57142857 10. ]
Output: [-2.99822295 -2.84496713 -2.66412441 -2.44368627 -2.16177575 -1.77227614
-1.15447739 0. 1.15447739 1.77227614 2.16177575 2.44368627
2.66412441 2.84496713 2.99822295]
Last Updated :
07 Jan, 2022
Like Article
Save Article
Share your thoughts in the comments
Please Login to comment...