Struct LayerNorm

pub struct LayerNorm<B: Backend> {
    pub weight: Option<Tensor<B>>,
    pub bias: Option<Tensor<B>>,
    pub eps: f32,
    /* private fields */
}

Lyaer norm layer

Fields

weight: Option<Tensor<B>>

weight

bias: Option<Tensor<B>>

bias

eps: f32

a value added to the denominator for numerical stability

Implementations

impl<B: Backend> LayerNorm<B>

pub fn forward(&self, x: &Tensor<B>) -> Tensor<B>

Forward function for layer_norm.

Trait Implementations

impl<'a, B: Backend> IntoIterator for &'a LayerNorm<B>

type Item = &'a Tensor<B>

The type of the elements being iterated over.

type IntoIter = IntoIter<&'a Tensor<B>>

Which kind of iterator are we turning this into?

fn into_iter(self) -> Self::IntoIter

Creates an iterator from a value.

impl<'a, B: Backend> IntoIterator for &'a mut LayerNorm<B>

type Item = &'a mut Tensor<B>

The type of the elements being iterated over.

type IntoIter = IntoIter<<&'a mut LayerNorm<B> as IntoIterator>::Item>

Which kind of iterator are we turning this into?

fn into_iter(self) -> Self::IntoIter

Creates an iterator from a value.