Pytorch根据向量批量构造对角矩阵

最新推荐文章于 2024-03-06 19:00:00 发布

wangchaoxjtu

最新推荐文章于 2024-03-06 19:00:00 发布

阅读量1.5k

点赞数

本文链接：https://blog.youkuaiyun.com/wangchaoxjtu/article/details/117394743

版权

torch.diag_embed函数用于根据输入向量批量构造对角矩阵。该函数可以选择指定的对角线（主对角线或上/下对角线），并自适应调整输出矩阵的大小以匹配输入向量的维度。使用offset参数可以控制对角线的位置，dim1和dim2参数定义了二维平面。将diag_embed应用于输出会得到与输入相同的矩阵，但需要注意默认的维度设置可能需要明确指定。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

TORCH.DIAG_EMBED

torch.diag_embed(input, offset=0, dim1=-2, dim2=-1) → Tensor

Creates a tensor whose diagonals of certain 2D planes (specified by dim1 and dim2) are filled by input. To facilitate creating batched diagonal matrices, the 2D planes formed by the last two dimensions of the returned tensor are chosen by default.

The argument offset controls which diagonal to consider:

If offset = 0, it is the main diagonal.
If offset > 0, it is above the main diagonal.
If offset < 0, it is below the main diagonal.

The size of the new matrix will be calculated to make the specified diagonal of the size of the last input dimension. Note that for offset other than 00 , the order of dim1 and di