TensorFlow: using a tensor to index another tensor

Question

I have a basic question about how to do indexing in TensorFlow.

In numpy:

x = np.asarray([1,2,3,3,2,5,6,7,1,3])
e = np.asarray([0,1,0,1,1,1,0,1])
#numpy 
print x * e[x]

I can get

[1 0 3 3 0 5 0 7 1 3]

How can I do this in TensorFlow?

x = np.asarray([1,2,3,3,2,5,6,7,1,3])
e = np.asarray([0,1,0,1,1,1,0,1])
x_t = tf.constant(x)
e_t = tf.constant(e)
with tf.Session():
    ????

Thanks!

stackoverflow.com/questions/33736795/… isn't it what you're asking about? — Alleo
– Alleo, Commented Mar 7, 2016 at 12:02

David Parks · Accepted Answer · 2018-10-15 17:59:49Z

36

Fortunately, the exact case you're asking about is supported in TensorFlow by tf.gather():

result = x_t * tf.gather(e_t, x_t)

with tf.Session() as sess:
    print sess.run(result)  # ==> 'array([1, 0, 3, 3, 0, 5, 0, 7, 1, 3])'

The tf.gather() op is less powerful than NumPy's advanced indexing: it only supports extracting full slices of a tensor on its 0th dimension. Support for more general indexing has been requested, and is being tracked in this GitHub issue.

edited Oct 15, 2018 at 17:59

David Parks

32.4k48 gold badges206 silver badges366 bronze badges

answered Mar 7, 2016 at 15:40

mrry

126k27 gold badges404 silver badges401 bronze badges

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

2 Comments

fritzo Over a year ago

Tensorflow now has a more powerful tf.gather_nd() op.

BiBi Over a year ago

Also, tf.gather now supports any axis, not only the 0th dimension, with the argument axis.

Collectives™ on Stack Overflow

TensorFlow: using a tensor to index another tensor

1 Answer 1

2 Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related