Struct MultiHeadAttention

Source

pub struct MultiHeadAttention;

Expand description

Multi-Headed attention is the first evolution of the Scaled Dot-Product Attention mechanism. They allow the model to jointly attend to information from different representation subspaces at different positions.

Auto Trait Implementations§

§

impl UnwindSafe for MultiHeadAttention

Blanket Implementations§

Source §

impl<T> Any for T
where T: 'static + ?Sized,

Source §

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more

Source §

impl<T> Borrow<T> for T
where T: ?Sized,

Source §

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more

Source §

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source §

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more

Source §

impl<T> CallInPlace<T> for T
where T: CallInto<T>,

Source §

fn call_inplace<F>(&mut self, f: F) -> <T as CallInto<T>>::Output
where F: FnMut(&mut T) -> <T as CallInto<T>>::Output,

The call_on_mut method allows an object to be passed onto a function that takes a mutable reference to the object. This is useful for cases where you want to perform an operation on an object and mutate it in the process.

Source §

impl<T> CallInto<T> for T

Source §

type Output = T

Source §

fn call_into<F>(self, f: F) -> <T as CallInto<T>>::Output
where F: FnOnce(T) -> <T as CallInto<T>>::Output,

The call_into method allows an object to be passed into a function that takes ownership of the object. This is useful for cases where you want to perform an operation on an object and consume it in the process.

Source §

impl<T> CallOn<T> for T
where T: CallInto<T>,

Source §

fn call_on<F>(&self, f: F) -> <T as CallInto<T>>::Output
where F: FnMut(&T) -> <T as CallInto<T>>::Output,

The call_on method allows an object to be passed onto a function that takes a reference to the object. This is useful for cases where you want to perform an operation on an object without needing to extract it from a container or context.

Source §