Function softmin 

pub fn softmin<const D: usize>(
    tensor: Tensor<D>,
    dim: impl AsIndex,
) -> Tensor<D>

Applies the softmin function on the input tensor along the given dimension.

softmin(x_i) = exp(-x_i) / sum_j(exp(-x_j)

Arguments

• dim: the dimension along which Softmin will be computed. Negative dimensions are supported and count from the end.

Panics

• If dim is outside [-D, D)