Function softmin

pub fn softmin<const D: usize, B>(
    tensor: Tensor<B, D>,
    dim: usize,
) -> Tensor<B, D>
where
    B: Backend,

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

$$ \text{softmin}(x_i) = \frac{\exp(-x_i)}{\sum_j \exp(-x_j)} $$

Arguments

• dim: the dimension along which Softmax will be computed.

Panics

• If dim is outside [0, D)