Python | Tensorflow reciprocal() method

0 0 1 minute read

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.reciprocal() [alias tf.math.reciprocal] provides support to calculate the reciprocal of input in Tensorflow. It expects the input in form of complex numbers as $a+bi$ , floating point numbers and integers. The input type is tensor and if the input contains more than one element, an element-wise reciprocal is computed, $y=1/x$ .

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

Parameters:
x: A Tensor of type bfloat16, half, float32, float64, int32, int64, complex64 or complex128.
name (optional): The name for the operation.

Return type: A Tensor with the same size and type as that of x.

Code #1:

Python3

# Importing the Tensorflow library 
import tensorflow as tf 
  
# A constant vector of size 6 
a = tf.constant([-0.5, -0.1, 0, 0.1, 0.5, 2], dtype = tf.float32) 
  
# Applying the reciprocal function and 
# storing the result in 'b' 
b = tf.reciprocal(a, name ='reciprocal') 
  
# 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:0", shape=(6, ), dtype=float32)
Input: [-0.5 -0.1  0.   0.1  0.5  2. ]
Return type: Tensor("reciprocal:0", shape=(6, ), dtype=float32)
Output: [ -2.  -10.    inf  10.    2.    0.5]

$inf$ denotes that the reciprocal approaches to infinity as the input approaches to zero.

Code #2: Visualization

Python3

# Importing the Tensorflow library 
import tensorflow as tf 
  
# Importing the NumPy library 
import numpy as np 
  
# Importing the matplotlib.pyplot function 
import matplotlib.pyplot as plt 
  
# Two vector each of size 20 with values from 0 to 10 
a = np.linspace(0, 10, 20) 
  
# Applying the reciprocal function and 
# storing the result in 'b' 
b = tf.reciprocal(a, name ='reciprocal') 
  
# 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.reciprocal")  
    plt.xlabel("X")  
    plt.ylabel("Y")  
    plt.grid() 
  
    plt.show() 

Output:

Input: [ 0.          0.52631579  1.05263158  1.57894737  2.10526316  2.63157895
  3.15789474  3.68421053  4.21052632  4.73684211  5.26315789  5.78947368
  6.31578947  6.84210526  7.36842105  7.89473684  8.42105263  8.94736842
  9.47368421 10.        ]
Output: [       inf 1.9        0.95       0.63333333 0.475      0.38
 0.31666667 0.27142857 0.2375     0.21111111 0.19       0.17272727
 0.15833333 0.14615385 0.13571429 0.12666667 0.11875    0.11176471
 0.10555556 0.1       ]