Python – tensorflow.math.less()

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

less() is used to find element wise truth value of x<y. It supports broadcasting

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

Parameters:

  • x: It is a tensor. Allowed dtypes are float32, float64, int32, uint8, int16, int8, int64, bfloat16, uint16, half, uint32, uint64.
  • y: It is a tensor of same dtype as x.
  • name(optional): It defines the name of the operation

Returns: It returns a tensor of type bool.



Example 1:

Python3

filter_none

edit
close

play_arrow

link
brightness_4
code

# importing the library
import tensorflow as tf
  
# Initializing the input tensor
a = tf.constant([7, 8, 13, 11], dtype = tf.float64)
b = tf.constant([2, 13, 14, 5],  dtype = tf.float64)
  
# Printing the input tensor
print('a: ', a)
print('b: ', b)
  
# Finding truth value
res = tf.math.less(x = a, y = b)
  
# Printing the result
print('Result: ', res)

chevron_right


Output:

a:  tf.Tensor([ 7.  8. 13. 11.], shape=(4, ), dtype=float64)
b:  tf.Tensor([ 2. 13. 14.  5.], shape=(4, ), dtype=float64)
Result:  tf.Tensor([False  True  True False], shape=(4, ), dtype=bool)


Example 2: In this example broadcasting will be performed on input.

Python3

filter_none

edit
close

play_arrow

link
brightness_4
code

# Importing the libraray
import tensorflow as tf
  
# Initializing the input tensor
a = tf.constant([7, 8, 13, 11], dtype = tf.float64)
b = (9)
  
# Printing the input tensor
print('a: ', a)
print('b: ', b)
  
# Finding truth value
res = tf.math.less(x = a, y = b)
  
# Printing the result
print('Result: ', res)

chevron_right


Output:

a:  tf.Tensor([ 7.  8. 13. 11.], shape=(4, ), dtype=float64)
b:  9
Result:  tf.Tensor([ True  True False False], shape=(4, ), dtype=bool)



My Personal Notes arrow_drop_up

Check out this Author's contributed articles.

If you like GeeksforGeeks and would like to contribute, you can also write an article using contribute.geeksforgeeks.org or mail your article to contribute@geeksforgeeks.org. See your article appearing on the GeeksforGeeks main page and help other Geeks.

Please Improve this article if you find anything incorrect by clicking on the "Improve Article" button below.