CODEWITHSUNDEEP
tensorflow
far-zadeh
far-zadeh

Reputation: 145

Aggregate each element of tensor in tensorflow

I have a tensor 3-D as follow:

A=array([[[False, False, False],
        [False, False,  True],
        [False,  True,  True],
        [ True,  True,  True],
        [ True,  True, False]]], dtype=bool)
        A.shape= (1,5,3)

I would like to convert it to 2-D tensor in tensorflow in graph where if I have a True in any element the aggregate result should be True, otherwise mush be False. Like follows:

output=array([[False, True, True, True, True]], dtype=bool)
output.shape= (1,5)

Upvotes: 0

Views: 747

Answers (1)

natschz
natschz

Reputation: 1117

This should do exactly what you want (directly from the documentation):

# 'x' is [[True,  True]
#         [False, False]]
tf.reduce_any(x) ==> True
tf.reduce_any(x, 0) ==> [True, True]
tf.reduce_any(x, 1) ==> [True, False]   <== this is what you need

https://www.tensorflow.org/versions/r0.7/api_docs/python/math_ops.html#reduce_any

Upvotes: 1

Related Questions