如何在 TensorFlow 中无周期性边界滚动? [英] How to roll without periodic boundaries in TensorFlow?

问题描述

我需要一个与滚动非常相似的张量的转换.不同之处在于我不希望轴末端的值出现在开头.换句话说，例如，我希望第二个元素位于 3d 位置，但我不希望最后一个元素成为第一个元素.相反，我希望第一个元素为零.

I need a transformation of a tensor which is very similar to roll. The difference is that I do not want the values from the end of the axis to appear in the beginning. In other words I want, for example, the 2nd element to be on 3d place but I do not want the last element to become the first one. Instead, I want the first elements to be zeros.

我已经试过了:

prev_xs = tf.roll(xs, shift = 1, axis = 1)
prev_xs[:,0] = 0.0

然而，它不起作用，因为

However, it does not work because

TypeError: 'Tensor' object does not support item assignment

那么，问题的正确解决方案是什么?

So, what is the proper solution of the problem?

推荐答案

你可以使用

prev_xs = tf.concat((tf.zeros([tf.shape(xs)[0], 1]), xs[:, :1]), axis=1)

一步一步，我们通过像[:, :1]这样的索引来丢弃xs的最后一列.我们创建一列具有适当行数的零.然后我们将它连接在 xs 前面，将每一列向后推 1.

Step-by-step, we discard the last column of xs by indexing like [:, :1]. We create a column of zeros with the appropriate number of rows. Then we concatenate it in front of xs, pushing every column back by 1.

这篇关于如何在 TensorFlow 中无周期性边界滚动?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！