use tensorflow to get value from a value tensor by index tensor

Question

There is a index tensor like this: [[1,2,3],[1,2,3]] (shape is batch * length)

and there is a value tensor like this: (shape is batch * length * deep)

[[[0.9,0.9,0.1,0.1],[0.9,0.1,0.8,0.1],[0.9,0.1,0.1,0.6]],
[[0.1,0.9,0.8,1],[1,2,0.8,0.1],[0.1,0.1,2,0.6]]].

how can I get [[0.9,0.8,0.6],[0.9,0.8,0.6]] with tensorflow?

The problem I had was taking a row of values and using it as an index in the last dimension of another matrix, corresponding values. It's not about the maximum — Rxma
– Rxma, Commented Sep 26, 2020 at 1:07

The Guy with The Hat · Accepted Answer · 2020-09-26 01:20:57Z

2

I'm not sure that this is the best solution, but it works: tf.gather_nd(values, tf.expand_dims(index, -1), batch_dims=2)

e.g.:

>>> index = tf.constant([[1,2,3],[1,2,3]])
>>> values = tf.constant([[[0.9,0.9,0.1,0.1],[0.9,0.1,0.8,0.1],[0.9,0.1,0.1,0.6]],[[0.1,0.9,0.8,1],[1,2,0.8,0.1],[0.1,0.1,2,0.6]]])
>>> result = tf.gather_nd(values, tf.expand_dims(index, -1), batch_dims=2)
>>> result.eval()
array([[0.9, 0.8, 0.6],
       [0.9, 0.8, 0.6]], dtype=float32)

answered Sep 26, 2020 at 1:20

The Guy with The Hat

11.2k10 gold badges63 silver badges83 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

use tensorflow to get value from a value tensor by index tensor

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related