在torch.sum() 中dim=-1 或-2 是什么意思? [英] what does dim=-1 or -2 mean in torch.sum()?

问题描述

让我以二维矩阵为例:

mat = torch.arange(9).view(3, -1)

tensor([[0, 1, 2],
        [3, 4, 5],
        [6, 7, 8]])

torch.sum(mat, dim=-2)

tensor([ 9, 12, 15])

我发现 torch.sum(mat, dim=-2) 的结果等于 torch.sum(mat, dim=0) 和 dim=-1 等于 dim=1.我的问题是如何理解这里的负面维度.如果输入矩阵有 3 个或更多维度怎么办?

I find the result of torch.sum(mat, dim=-2) is equal to torch.sum(mat, dim=0) and dim=-1 equal to dim=1. My question is how to understand the negative dimension here. What if the input matrix has 3 or more dimensions?

推荐答案

减号本质上意味着您向后浏览维度.设 A 是一个 n 维矩阵.然后dim=n-1=-1，dim=n-2=-2，...，dim=1=-(n-1)，dim=0=-n.有关详细信息，请参阅 numpy 文档，因为 pytorch 在很大程度上基于 numpy.

The minus essentially means you go backwards through the dimensions. Let A be a n-dimensional matrix. Then dim=n-1=-1, dim=n-2=-2, ..., dim=1=-(n-1), dim=0=-n. See the numpy doc for more information, as pytorch is heavily based on numpy.

这篇关于在torch.sum() 中dim=-1 或-2 是什么意思?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！