torch.index_select

Wanderer001

已于 2023-11-02 20:32:15 修改

阅读量2.2k

点赞数 4

分类专栏： Pytorch 文章标签： python 深度学习机器学习

于 2022-08-19 17:47:32 首次发布

本文链接：https://blog.csdn.net/weixin_36670529/article/details/101775296

版权

torch.index_select函数用于根据指定维度上的索引返回一个新的张量，该张量与原始张量具有相同数量的维度，指定维度的大小与索引张量的长度相同，其他维度的大小保持不变。注意返回的张量不共享原始张量的存储。如果索引张量形状不正确，会自动调整并可能重新分配存储。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

torch.index_select(input, dim, index, out=None) → Tensor

Returns a new tensor which indexes the input tensor along dimension dim using the entries in index which is a LongTensor.

The returned tensor has the same number of dimensions as the original tensor (input). The dimth dimension has the same size as the length of index; other dimensions have the same size as in the original tensor.

Note

The returned tensor does not use the same storage as the original tensor. If out has a different shape than expected, we silently change it to the correct shape, reallocating the underlying storage if necessary.

Parameters