从 Tensorflow 中的张量中删除一组张量 [英] Remove a set of tensors from a tensor in Tensorflow

问题描述

我正在寻找一种简单的方法来从 Tensorflow 中的当前张量中删除一组张量，但我有一个困难的合理解决方案.

I'm looking for an easy way to remove a set of tensors from a current tensor in Tensorflow and I'm having a difficult reasonable solution.

例如，假设我有以下当前张量:

For example, let's say that I have the below current tensor:

a = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[2, 3], name='a')

而且我想从这个张量(2.0 和 5.0)中删除两个项目.

And that I want to remove, say, two items from this tensor (2.0 and 5.0).

在创建后将这个张量转换为 [1.0, 3.0, 4.0, 6.0] 的最佳方法是什么?

What would be the best way to transform this tensor into [1.0, 3.0, 4.0, 6.0] after it has been created?

非常感谢.

推荐答案

您可以调用 tf.unstack 来获取子张量列表.然后你可以修改列表并调用 tf.stack 从列表中构造一个张量.例如，以下代码从 a 中删除 [2.0, 5.0] 列:

You can call tf.unstack to obtain a list of sub-tensors. Then you can modify the list and call tf.stack to construct a tensor from the list. For example, the following code removes the [2.0, 5.0] column from a:

a = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[2, 3], name='a')
a_vecs = tf.unstack(a, axis=1)
del a_vecs[1]
a_new = tf.stack(a_vecs, 1)

这篇关于从 Tensorflow 中的张量中删除一组张量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！