Python - tensorflow.math.lbeta()

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

lbeta() is used to compute ln(|Beta(x)|). It reduces the tensor along the last dimension. If one-dimensional z is [z1, ..., zk], then Beta(z) is defined as

If x is n+1 dimensional tensor with shape [N₁ , . . ., N_n , k], last dimension is treated as z vector and,

If z = [u, v] then traditional bivariate beta function is defined as 

Syntax: tensorflow.math.lbeta( x, name)

Parameters:

• x: It's the input tensor with rank n+1 where n>=0. Allowed dtypes  are float, or double.
• name(optional): It defines the name for the operation.

Returns:

It returns the logarithm of |Beta(x)| reducing along the last dimension. 

Example 1:

# Importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([[7, 8], [13, 11]], dtype = tf.float64)

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

# Calculating the result
res = tf.math.lbeta(x = a)

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

Output:

a:  tf.Tensor(
[[ 7.  8.]
 [13. 11.]], shape=(2, 2), dtype=float64)
Result:  tf.Tensor([-10.08680861 -16.5150485 ], shape=(2, ), dtype=float64)

Example 2:

# Importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([7, 8, 13, 11], dtype = tf.float64)

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

# Calculating the result
res = tf.math.lbeta(x = a)

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

Output:

a:  tf.Tensor([ 7.  8. 13. 11.], shape=(4, ), dtype=float64)
Result:  tf.Tensor(-52.77215897270088, shape=(), dtype=float64)