Pytorch根据向量批量构造对角矩阵

TORCH.DIAG_EMBEDtorch.diag_embed(input,offset=0,dim1=-2,dim2=-1)→ TensorCreates a tensor whose diagonals of certain 2D planes (specified bydim1anddim2) are filled byinput. To facilitate creating batched diagonal matrices, the 2D planes formed b...
摘要由CSDN通过智能技术生成

TORCH.DIAG_EMBED

torch.diag_embed(inputoffset=0dim1=-2dim2=-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

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值