nnf_softmin function

Softmin

Softmin

Applies a softmin function.

nnf_softmin(input, dim, dtype = NULL)

Arguments

  • input: (Tensor) input
  • dim: (int) A dimension along which softmin will be computed (so every slice along dim will sum to 1).
  • dtype: (torch.dtype, optional) the desired data type of returned tensor. If specified, the input tensor is casted to dtype before the operation is performed. This is useful for preventing data type overflows. Default: NULL.

Details

Note that

Softmin(x)=Softmax(−x) Softmin(x) = Softmax(-x)

.

See nnf_softmax definition for mathematical formula.

torch packageRead PDF manual
  • Maintainer: Daniel Falbel
  • License: MIT + file LICENSE
  • Last published: 2025-02-14

Useful links