Python – tensorflow.math.polygamma()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning  neural networks.

polygamma() is used to compute polygamma function. Polygamma function is defined as:

This function is defined for only non-negative integer orders i.e. value of a should be non-negative.

Syntax: tensorflow.math.polygamma( a, x, name)

Parameters:

• a: It’s a tensor of non-negative values. Allowed dtypes are  float32, float64.
• x: It’s a tensor of same dtype as a.
• name(optional): It defines the name for the operation.

Returns:

It returns a tensor of same dtype as a.

Example 1:

Python3

# importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([1, 2, 3], dtype = tf.float64)
x = tf.constant([7, 9, 13], dtype = tf.float64)

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

# Calculating result
res = tf.math.polygamma(a, x)

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

Output:

a:  tf.Tensor([1. 2. 3.], shape=(3, ), dtype=float64)
x:  tf.Tensor([ 7.  9. 13.], shape=(3, ), dtype=float64)
Result:  tf.Tensor([ 0.15354518 -0.01379332  0.00102074], shape=(3, ), dtype=float64)

Example 2: For negative value of a returned output is nan.

Python3

# importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([-1, 2, 3], dtype = tf.float64)
x = tf.constant([7, 9, 13], dtype = tf.float64)

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

# Calculating Result
res = tf.math.polygamma(a, x)

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

Output:

a:  tf.Tensor([-1.  2.  3.], shape=(3, ), dtype=float64)
x:  tf.Tensor([ 7.  9. 13.], shape=(3, ), dtype=float64)
Result:  tf.Tensor([        nan -0.01379332  0.00102074], shape=(3, ), dtype=float64)