Struct SelfAttention

pub struct SelfAttention<F: Float + Debug> { /* private fields */ }

Self-attention layer that uses the same input for query, key, and value

This is a convenience wrapper around the MultiHeadAttention layer for the common case of self-attention, where the query, key, and value are all derived from the same input.

Implementations

impl<F: Float + Debug + ScalarOperand + 'static> SelfAttention<F>

pub fn new<R: Rng>( d_model: usize, config: AttentionConfig, rng: &mut R, ) -> Result<Self>

Create a new self-attention layer

Arguments

• d_model - Embedding dimension
• config - Attention configuration
• rng - Random number generator for weight initialization

Returns

• A new self-attention layer

Trait Implementations

impl<F: Float + Debug + ScalarOperand + 'static> Clone for SelfAttention<F>

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<F: Debug + Float + Debug> Debug for SelfAttention<F>

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

Formats the value using the given formatter.

impl<F: Float + Debug + ScalarOperand + 'static> Layer<F> for SelfAttention<F>

fn as_any(&self) -> &dyn Any

Get the layer as a dyn Any for downcasting

fn as_any_mut(&mut self) -> &mut dyn Any

Get the layer as a mutable dyn Any for downcasting

fn forward(&self, input: &Array<F, IxDyn>) -> Result<Array<F, IxDyn>>

Forward pass of the layer

fn backward( &self, input: &Array<F, IxDyn>, grad_output: &Array<F, IxDyn>, ) -> Result<Array<F, IxDyn>>

Backward pass of the layer to compute gradients

fn update(&mut self, learning_rate: F) -> Result<()>

Update the layer parameters with the given gradients

fn params(&self) -> Vec<Array<F, IxDyn>>

Get the parameters of the layer

fn gradients(&self) -> Vec<Array<F, IxDyn>>

Get the gradients of the layer parameters

fn set_gradients(&mut self, _gradients: &[Array<F, IxDyn>]) -> Result<()>

Set the gradients of the layer parameters

fn set_params(&mut self, _params: &[Array<F, IxDyn>]) -> Result<()>

Set the parameters of the layer

fn set_training(&mut self, _training: bool)

Set the layer to training mode (true) or evaluation mode (false)

fn is_training(&self) -> bool

Get the current training mode

fn layer_type(&self) -> &str

Get the type of the layer (e.g., “Dense”, “Conv2D”)

fn parameter_count(&self) -> usize

Get the number of trainable parameters in this layer

fn layer_description(&self) -> String

Get a detailed description of this layer

impl<F: Float + Debug + ScalarOperand + 'static> ParamLayer<F> for SelfAttention<F>

fn get_parameters(&self) -> Vec<&Array<F, IxDyn>>

Get the parameters of the layer as a vector of arrays

fn get_gradients(&self) -> Vec<&Array<F, IxDyn>>

Get the gradients of the parameters

fn set_parameters(&mut self, params: Vec<Array<F, IxDyn>>) -> Result<()>

Set the parameters of the layer