class torch.nn.Softmin(dim: Optional[int] = None)
[source]
Applies the Softmin function to an n-dimensional input Tensor rescaling them so that the elements of the n-dimensional output Tensor lie in the range [0, 1]
and sum to 1.
Softmin is defined as:
*
means, any number of additional dimensionsdim (int) – A dimension along which Softmin will be computed (so every slice along dim will sum to 1).
a Tensor of the same dimension and shape as the input, with values in the range [0, 1]
Examples:
>>> m = nn.Softmin() >>> input = torch.randn(2, 3) >>> output = m(input)
© 2019 Torch Contributors
Licensed under the 3-clause BSD License.
https://pytorch.org/docs/1.7.0/generated/torch.nn.Softmin.html