Function quiet_softmax

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

Applies the “quiet softmax” function on the input tensor along the given dimension.

This function is similar to the softmax function, but it allows for “no selection” when all the outputs are close to zero.

$$ \text{quiet\_softmax}(x_i) = \frac{\exp(x_i)}{1 + \sum_j \exp(x_j)} $$

Arguments

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

Panics

• If dim is outside [0, D)