Python - Tensorflow bitwise.right_shift() method

Last Updated : 04 Jun, 2020

Tensorflow bitwise.right_shift() method performs the right_shift operation on input a defined by input b and return the new constant. The operation is done on the representation of a and b. This method belongs to bitwise module.

Syntax: tf.bitwise.right_shift( a, b, name=None) Arguments

a: This must be a Tensor. It should be from the one of the following types: int8, int16, int32, int64, uint8, uint16, uint32, uint64.

b: This should also be a Tensor, Type same as a.

name: This is optional parameter and this is the name of the operation.

Return: It returns a Tensor having the same type as a and b.

Let's see this concept with the help of few examples: Example 1:

Python3

# Importing the Tensorflow library 
import tensorflow as tf 

# A constant a and b
a = tf.constant(256, dtype = tf.int32)
b = tf.constant(1, dtype = tf.int32)  

# Applying the right_shift() function 
# storing the result in 'c' 
c = tf.bitwise.right_shift(a, b) 

# Initiating a Tensorflow session 
with tf.Session() as sess:
    print("Input 1", a)
    print(sess.run(a))
    print("Input 2", b)
    print(sess.run(b))
    print("Output: ", c)
    print(sess.run(c))

Output:

Input 1 Tensor("Const_57:0", shape=(), dtype=int32)
256
Input 2 Tensor("Const_58:0", shape=(), dtype=int32)
1
Output:  Tensor("RightShift_3:0", shape=(), dtype=int32)
128

Example 2:

Python3

# Importing the Tensorflow library 
import tensorflow as tf 

# A constant a and b
a = tf.constant([8, 16, 32], dtype = tf.int32)
b = tf.constant([2, 2, 3], dtype = tf.int32)  

# Applying the right_shift() function 
# storing the result in 'c' 
c = tf.bitwise.right_shift(a, b) 

# Initiating a Tensorflow session 
with tf.Session() as sess:
    print("Input 1", a)
    print(sess.run(a))
    print("Input 2", b)
    print(sess.run(b))
    print("Output: ", c)
    print(sess.run(c))

Output:

Input 1 Tensor("Const_53:0", shape=(3, ), dtype=int32)
[ 8 16 32]
Input 2 Tensor("Const_54:0", shape=(3, ), dtype=int32)
[2 2 3]
Output:  Tensor("RightShift_1:0", shape=(3, ), dtype=int32)
[2 4 4]