Python | Tensorflow abs () method

The tensorflow.math module provides support for many basic mathematical operations. The tf.abs () [alias tf.math.abs ] function provides support for absolute functions in Tensorflow. Expected to be input as complex numbers in the form or floating point. Input type — tensor, and if the input contains more than one element, the element-wise absolute value is calculated.

For a complex number the absolute value is calculated as ,
For floating point numbers the absolute value is calculated as

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

Parameters :
x : A Tensor or SparseTensor of type float16, float32, float64, int32, int64, complex64 or complex128.
name (optional): The name for the operation.

Return type : A Tensor or SparseTensor with the same size and type as that of x with absolute values. For complex64 or complex128 input, the returned Tensor will be of type float32 or float64, respectively.

Code # 1: For Floats

# Import Tensorflow library

import tensorflow as tf

 
# Constant vector of size 5

a = tf.constant ([ - 0.5 , - 0.1 , 0 , 0.1 , 0.5 ] , dtype = tf.float32)

  
# Applying the abs function and
# saving the result to & # 39; b & # 39;

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

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

  print ( ` Input type: ` , a)

print ( < code class = "string"> `Input:` , sess.run (a))

  print ( `Return type:` , b)

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

Output:

 Input type: Tensor ( "Const: 0", shape = (5,), dtype = float32) Input: [-0.5 -0.1 0. 0.1 0.5] Return Type: Tensor ("abs: 0", shape = (5,), dtype = float32 ) Output: [0.5 0.1 0. 0.1 0.5] 

Code # 2: Rendering

# Import Tensorflow library

import tensorflow as tf

 
# Import NumPy library

import numpy as np

  
# Import of the matplotlib.pylot function

import matplotlib.pyplot as plt

 
# Vector size 11 with values ​​from - 5 to 5

a = np. linspace ( - 5 , 5 , 11 )

 
# Applying an absolute function and
# save the result to & # 39; b & # 39;

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

  
# 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.abs"

plt.xlabel ( "X"

plt.ylabel ( "Y"

  

  plt.show ()

Output:

 Input: [-5. -four. -3. -2. -one. 0. 1. 2. 3. 4. 5.] Output: [5. 4. 3. 2. 1. 0. 1. 2. 3. 4. 5.] 

Code # 3: for complex numbers

# Import Tensorflow library

import tensorflow as tf

  
# Constant vector of size 2

a = tf.constant ([[ - 2.25 + 4.75j ], [ - 3.25 + 5.75j ]],

  dtype = tf.complex64)

 
# Applying the abs function and
# saving the result to & # 39; b & # 39;

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

  
# 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))

Output:

 Input type: Tensor ("Const_1: 0", shape = (2, 1), dtype = complex64) Input: [[-2.25 + 4.75j] [-3.25 + 5.75j]] Return Type: Tensor ( "abs_1: 0", shape = (2, 1), dtype = float32) Output: [[5.255949] [6.6049223]]