“解压"是什么意思在 Pytorch 中做什么? [英] What does "unsqueeze" do in Pytorch?

问题描述

我无法理解 PyTorch 文档 中的示例如何对应解释:

<块引用>

返回一个新的张量，其尺寸为 1，插入到指定位置.[...]

<预><代码>>>>x = torch.tensor([1, 2, 3, 4])>>>torch.unsqueeze(x, 0)张量([[ 1, 2, 3, 4]])>>>torch.unsqueeze(x, 1)张量([[ 1],[2],[3],[4]])

解决方案

如果你看前后数组的形状，你会发现它之前是 (4,) 和之后是 (1, 4)(当第二个参数是 0)和 (4, 1)(当第二个参数是 1).因此，根据第二个参数的值，将 1 插入到 0 或 1 轴的数组形状中.

这与 np.squeeze() 相反(从 MATLAB 中借用的命名法)，它删除了大小为 1(单例)的轴.

I cannot understand how the example in the PyTorch documentation corresponds to the explanation:

Returns a new tensor with a dimension of size one inserted at the specified position. [...]

>>> x = torch.tensor([1, 2, 3, 4])
>>> torch.unsqueeze(x, 0)
tensor([[ 1,  2,  3,  4]])
>>> torch.unsqueeze(x, 1)
tensor([[ 1],
        [ 2],
        [ 3],
        [ 4]])

解决方案

If you look at the shape of the array before and after, you see that before it was (4,) and after it is (1, 4) (when second parameter is 0) and (4, 1) (when second parameter is 1). So a 1 was inserted in the shape of the array at axis 0 or 1, depending on the value of the second parameter.

That is opposite of np.squeeze() (nomenclature borrowed from MATLAB) which removes axes of size 1 (singletons).

这篇关于“解压"是什么意思在 Pytorch 中做什么?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！