# Tensorflow bitwise.bitwise_xor() method – Python

• Last Updated : 26 May, 2020

Tensorflow `bitwise.bitwise_xor()` method performs the bitwise_xor operation and the result will set those bits, that are different in a and b. The operation is done on the representation of a and b. This method belongs to bitwise module.

Syntax: `tf.bitwise.bitwise_xor(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:

 `# Importing the Tensorflow library ``import` `tensorflow as tf `` ` `# A constant a and b ``a ``=` `tf.constant(``43``, dtype ``=` `tf.int32) ``b ``=` `tf.constant(``5``, dtype ``=` `tf.int32) `` ` `# Applying the bitwise_xor function ``# storing the result in 'c' ``c ``=` `tf.bitwise.bitwise_xor(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_36:0", shape=(), dtype=int32)
43
Input 2 Tensor("Const_37:0", shape=(), dtype=int32)
5
Output:  Tensor("BitwiseXor_4:0", shape=(), dtype=int32)
46
```

Example 2:

 `# Importing the Tensorflow library ``import` `tensorflow as tf `` ` `# A constant vector of size 2 ``a ``=` `tf.constant([``10``, ``6``], dtype ``=` `tf.int32) ``b ``=` `tf.constant([``12``, ``5``], dtype ``=` `tf.int32) `` ` `# Applying the bitwise_xor function ``# storing the result in 'c' ``c ``=` `tf.bitwise.bitwise_xor(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_34:0", shape=(2, ), dtype=int32)
[10  6]
Input 2 Tensor("Const_35:0", shape=(2, ), dtype=int32)
[12  5]
Output:  Tensor("BitwiseXor_3:0", shape=(2, ), dtype=int32)
[6 3]
```

My Personal Notes arrow_drop_up