Function log_softmax

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

Applies the log softmax function on the input tensor along the given dimension.

$$ \text{log\_softmax}(x_i) = \log\left(\text{softmax}(x_i)\right) = \log\left(\frac{\exp(x_i)}{\sum_j \exp(x_j)}\right) $$

Arguments

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

Panics

• If dim is outside [0, D)