- torch.nn.functional.softmin(input, dim=None, _stacklevel=3, dtype=None)¶
Applies a softmin function.
Note that . See softmax definition for mathematical formula.
Softminfor more details.
input (Tensor) – input
dim (int) – A dimension along which softmin will be computed (so every slice along dim will sum to 1).
torch.dtype, optional) – the desired data type of returned tensor. If specified, the input tensor is casted to
dtypebefore the operation is performed. This is useful for preventing data type overflows. Default: None.
- Return type