Python – tensorflow.math.divide_no_nan()

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

divide_no_nan() is used to compute element wise safe division of x by y i.e it returns 0 if y is zero

Syntax: tensorflow.math.divide_no_nan( x, y, name)

Parameters:

• x: It is a tensor.
• y: It is a tensor.
• name(optional): It defines the name of the operation

Returns: It returns a tensor.

Example 1:

Python3

# importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([6, 8, 12, 15], dtype = tf.float64)
b = tf.constant([2, 3, 4, 5],  dtype = tf.float64)

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

# Calculating safe division
res = tf.math.divide_no_nan(x = a, y = b)

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

Output:

a:  tf.Tensor([ 6.  8. 12. 15.], shape=(4, ), dtype=float64)
b:  tf.Tensor([2. 3. 4. 5.], shape=(4, ), dtype=float64)
Result:  tf.Tensor([3.         2.66666667 3.         3.        ], shape=(4, ), dtype=float64)

Example 2: In this example one of the value in second tensor is taken 0.

Python3

# importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([6, 8, 12, 15], dtype = tf.float64)
b = tf.constant([2, 3, 4, 0],  dtype = tf.float64)

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

# Calculating safe division
res = tf.math.divide_no_nan(x = a, y = b)

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

Output:

a:  tf.Tensor([ 6.  8. 12. 15.], shape=(4, ), dtype=float64)
b:  tf.Tensor([2. 3. 4. 0.], shape=(4, ), dtype=float64)
Result:  tf.Tensor([3.         2.66666667 3.                0], shape=(4, ), dtype=float64)