【超简单】torch.narrow()函数

Pywin

已于 2023-01-12 21:37:01 修改

阅读量5.9w

点赞数 2

分类专栏： pytorch 文章标签： python 深度学习 pytorch

于 2020-06-04 17:03:03 首次发布

本文链接：https://blog.csdn.net/qq_36076233/article/details/106550966

版权

pytorch 专栏收录该内容

11 篇文章 0 订阅

订阅专栏

官方例子：

torch.narrow(input, dim, start, length) → Tensor

Returns a new tensor that is a narrowed version of input tensor. The dimension dim is input from start to start +length. The returned tensor and input tensor share the same underlying storage.

函数返回tensor的第dim维切片start: start+length的数据

Parameters

input (Tensor) – the tensor to narrow
dim (int) – the dimension along which to narrow
start (int) – the starting dimension
length (int) – the distance to the ending dimension

Example:

>>> x = torch.tensor([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
>>> torch.narrow(x, 0, 0, 2)
tensor([[ 1,  2,  3],
        [ 4,  5,  6]])

>>> torch.narrow(x, 1, 1, 1)
tensor([[ 2],
        [ 5],
        [ 8]])

>>> torch.narrow(x, 1, 1, 2)
tensor([[ 2,  3],
        [ 5,  6],
        [ 8,  9]])