Struct MultiHeadAttention 

pub struct MultiHeadAttention {
    pub heads: usize,
    pub d_model: usize,
    pub d_k: usize,
    pub w_q: Tensor,
    pub w_k: Tensor,
    pub w_v: Tensor,
    pub w_o: Tensor,
}

Fields

heads: usize

d_model: usize

d_k: usize

w_q: Tensor

w_k: Tensor

w_v: Tensor

w_o: Tensor

Implementations

impl MultiHeadAttention

pub fn new(heads: usize, d_model: usize) -> Self

pub fn forward(&self, input: &Tensor) -> Tensor

Forward pass. Input shape: (seq_len, d_model). Returns same shape.

pub fn parameter_count(&self) -> usize

Trait Implementations

impl Clone for MultiHeadAttention

fn clone(&self) -> MultiHeadAttention

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for MultiHeadAttention

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.