Python – tensorflow.math.reciprocal()

TensorFlow is open-source python library designed by Google to develop Machine Learning models and deep learning  neural networks. reciprocal() is used to find element wise reciprocal of x.

Syntax: tf.math.reciprocal(x, name)

Parameter:

• x: It’s the input tensor. Allowed dtype for this tensor are bfloat16, half, float32, float64, int32, int64, complex64, complex128.
• name(optional): It defines the name for the operation.

Returns: It returns a tensor of dtype same as x.

Example 1: This example uses reciprocal tensor.

Python3

# Importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([1, 2, -3, -4], dtype = tf.float64)

# Printing the input tensor
print('Input: ', a)

# Calculating result
res = tf.math.reciprocal(a)

# Printing the result
print('Result: ', res)

Output:

Input:  tf.Tensor([ 1.  2. -3. -4.], shape=(4, ), dtype=float64)
Result:  tf.Tensor([ 1.          0.5        -0.33333333 -0.25      ], shape=(4, ), dtype=float64)

Example 2: This example uses complex tensor.

Python3

# importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([1 + 3j, 2-5j, -3 + 7j, -4-8j], dtype = tf.complex128)

# Printing the input tensor
print('Input: ', a)

# Calculating result
res = tf.math.reciprocal( a)

# Printing the result
print('Result: ', res)

Output:

Input:  tf.Tensor([ 1.+3.j  2.-5.j -3.+7.j -4.-8.j], shape=(4, ), dtype=complex128)
Result:  tf.Tensor(
[ 0.1       -0.3j         0.06896552+0.17241379j -0.05172414-0.12068966j
 -0.05      +0.1j       ], shape=(4, ), dtype=complex128)