Python – tensorflow.math.reduce_any()
Last Updated :
05 Aug, 2021
TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks.
reduce_any() is used to compute the “logical or” of elements across dimensions of a tensor.
Syntax: tensorflow.math.reduce_any( input_tensor, axis, keepdims, name)
Parameters:
- input_tensor: It is boolean tensor to reduce.
- axis(optional): It represent the dimensions to reduce. It’s value should be in range [-rank(input_tensor), rank(input_tensor)). If no value is given for this all dimensions are reduced.
- keepdims(optional): It’s default value is False. If it’s set to True it will retain the reduced dimension with length 1.
- name(optional): It defines the name for the operation.
Returns: It returns a tensor.
Example 1:
Python3
import tensorflow as tf
a = tf.constant([ True , False , False , True ], dtype = tf. bool )
print ( 'Input: ' , a)
res = tf.math.reduce_any(a)
print ( 'Result: ' , res)
|
Output:
Input: tf.Tensor([ True False False True], shape=(4, ), dtype=bool)
Result: tf.Tensor(True, shape=(), dtype=bool)
Example 2:
Python3
import tensorflow as tf
a = tf.constant([[ True , False ], [ False , True ]], dtype = tf. bool )
print ( 'Input: ' , a)
res = tf.math.reduce_any(a, axis = 1 , keepdims = True )
print ( 'Result: ' , res)
|
Output:
Input: tf.Tensor(
[[ True False]
[False True]], shape=(2, 2), dtype=bool)
Result: tf.Tensor(
[[ True]
[ True]], shape=(2, 1), dtype=bool)
Share your thoughts in the comments
Please Login to comment...