pub struct TransformerMetaLearning<T: Float + Debug + Send + Sync + 'static> { /* private fields */ }Expand description
Transformer meta-learning implementation
Implementations§
Source§impl<T: Float + Debug + Send + Sync + 'static + ScalarOperand> TransformerMetaLearning<T>
impl<T: Float + Debug + Send + Sync + 'static + ScalarOperand> TransformerMetaLearning<T>
Sourcepub fn new(config: &TransformerBasedOptimizerConfig<T>) -> Result<Self>
pub fn new(config: &TransformerBasedOptimizerConfig<T>) -> Result<Self>
Create new transformer meta-learning component
Sourcepub fn meta_step(
&mut self,
tasks: &[TaskBatch<T>],
support_data: &[Array2<T>],
query_data: &[Array2<T>],
) -> Result<MetaLearningResult<T>>
pub fn meta_step( &mut self, tasks: &[TaskBatch<T>], support_data: &[Array2<T>], query_data: &[Array2<T>], ) -> Result<MetaLearningResult<T>>
Perform meta-learning step
Sourcepub fn generate_update(
&mut self,
transformer_output: &Array2<T>,
current_parameters: &Array1<T>,
) -> Result<Array1<T>>
pub fn generate_update( &mut self, transformer_output: &Array2<T>, current_parameters: &Array1<T>, ) -> Result<Array1<T>>
Generate optimization update using meta-learned parameters
Sourcepub fn update_from_loss(&mut self, loss: T) -> Result<()>
pub fn update_from_loss(&mut self, loss: T) -> Result<()>
Update meta-learning state from loss
Sourcepub fn set_strategy(&mut self, strategy: MetaLearningStrategy)
pub fn set_strategy(&mut self, strategy: MetaLearningStrategy)
Set meta-learning strategy
Sourcepub fn get_strategy(&self) -> MetaLearningStrategy
pub fn get_strategy(&self) -> MetaLearningStrategy
Get current strategy
Auto Trait Implementations§
impl<T> Freeze for TransformerMetaLearning<T>where
T: Freeze,
impl<T> RefUnwindSafe for TransformerMetaLearning<T>where
T: RefUnwindSafe,
impl<T> Send for TransformerMetaLearning<T>
impl<T> Sync for TransformerMetaLearning<T>
impl<T> Unpin for TransformerMetaLearning<T>where
T: Unpin,
impl<T> UnsafeUnpin for TransformerMetaLearning<T>where
T: UnsafeUnpin,
impl<T> UnwindSafe for TransformerMetaLearning<T>where
T: UnwindSafe + RefUnwindSafe,
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more
Source§impl<T> IntoEither for T
impl<T> IntoEither for T
Source§fn into_either(self, into_left: bool) -> Either<Self, Self>
fn into_either(self, into_left: bool) -> Either<Self, Self>
Converts
self into a Left variant of Either<Self, Self>
if into_left is true.
Converts self into a Right variant of Either<Self, Self>
otherwise. Read moreSource§fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
Converts
self into a Left variant of Either<Self, Self>
if into_left(&self) returns true.
Converts self into a Right variant of Either<Self, Self>
otherwise. Read moreSource§impl<T> Pointable for T
impl<T> Pointable for T
Source§impl<SS, SP> SupersetOf<SS> for SPwhere
SS: SubsetOf<SP>,
impl<SS, SP> SupersetOf<SS> for SPwhere
SS: SubsetOf<SP>,
Source§fn to_subset(&self) -> Option<SS>
fn to_subset(&self) -> Option<SS>
The inverse inclusion map: attempts to construct
self from the equivalent element of its
superset. Read moreSource§fn is_in_subset(&self) -> bool
fn is_in_subset(&self) -> bool
Checks if
self is actually part of its subset T (and can be converted to it).Source§fn to_subset_unchecked(&self) -> SS
fn to_subset_unchecked(&self) -> SS
Use with care! Same as
self.to_subset but without any property checks. Always succeeds.Source§fn from_subset(element: &SS) -> SP
fn from_subset(element: &SS) -> SP
The inclusion map: converts
self to the equivalent element of its superset.