Tensorflow中某些元素的逆序 [英] Reverse order of some elements in Tensorflow

问题描述

假设我有一个形状为(M，N，2)的张量 DATA .我还有另一个由零和一组成的(N)形状的张量 IND .

Say I have a tensor DATA of shape (M, N, 2). I also have another tensor IND of shape (N) consisting of zeros and ones.

如果 IND(i)== 1 ，则 DATA(:，i，0)和 DATA(:，i，1)必须调换.如果 IND(i)== 0 ，它们将不会交换.

If IND(i)==1 then DATA(:,i,0) and DATA(:,i,1) have to swap. If IND(i)==0 they won't swap.

我该怎么做?我知道可以通过 tf.gather_nd 完成此操作，但是我不知道如何操作.

How can I do this? I know that this can be done via tf.gather_nd, but I have no idea how.

推荐答案

以下是 tf.equal ， tf.where ， tf.scater_nd_update ， tf.gather_nd 和 tf.reverse_v2 :

Here is one possible solution with tf.equal, tf.where, tf.scater_nd_update, tf.gather_nd and tf.reverse_v2:

data = tf.Variable([[[1, 2],
                     [2, 3],
                     [3, 4],
                     [4, 5],
                     [5, 6]]])  # shape=(1,5,2)

# reverse elements where ind is 1
ind = tf.constant([1, 0, 1, 0, 1])  # shape(5,)

cond = tf.where(tf.equal([ind], 1))
match_data = tf.gather_nd(data, cond)
rev_match_data = tf.reverse_v2(match_data, axis=[-1])
data = tf.scatter_nd_update(data, cond, rev_match_data)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print(sess.run(data))
    #[[[2 1]
    # [2 3]
    # [4 3]
    # [4 5]
    # [6 5]]]

这篇关于Tensorflow中某些元素的逆序的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！