Struct Softmax 

pub struct Softmax<D: Float, T, const RANK: usize> {
    pub dim: usize,
    /* private fields */
}

Softmax activation layer: normalizes along dim so values sum to 1.

Fields

dim: usize

The dimension to normalize along.

Implementations

impl<D: Float, T, const RANK: usize> Softmax<D, T, RANK>

pub fn new(dim: usize) -> Self

Creates a new Softmax layer.

Trait Implementations

impl<D: Float, const RANK: usize> Layer<SymTensor> for Softmax<D, SymTensor, RANK>

type Output = SymTensor

This layer’s output type.

fn call(&self, input: SymTensor) -> SymTensor

Applies this layer to input.

impl<D: Float, T: Tensor<D, RANK> + EagerTensor, const RANK: usize> Layer<T> for Softmax<D, T, RANK>

type Output = T

This layer’s output type.

fn call(&self, _input: T) -> Self::Output

Applies this layer to input.