Struct TransformerEncoderLayer 

pub struct TransformerEncoderLayer { /* private fields */ }

A single Transformer encoder layer.

Consists of multi-head self-attention followed by a position-wise feedforward network, each with residual connections and layer normalization.

Shape

• Input: (N, S, E) if batch_first (default)
• Output: (N, S, E)

where N=batch, S=source seq len, E=d_model.

Implementations

impl TransformerEncoderLayer

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

Creates a new TransformerEncoderLayer (post-norm, default).

Arguments

• d_model - Embedding dimension
• nhead - Number of attention heads
• dim_feedforward - Hidden dimension of feedforward network (default 2048)

pub fn new_with_pre_norm( d_model: usize, nhead: usize, dim_feedforward: usize, pre_norm: bool, ) -> Self

Creates a TransformerEncoderLayer with configurable norm ordering.

pub fn forward_with_mask( &self, src: &Variable, src_mask: Option<&Variable>, ) -> Variable

Forward pass with optional source mask.

Arguments

• src - Source sequence (N, S, E)
• src_mask - Optional attention mask

pub fn d_model(&self) -> usize

Returns the model dimension.

Trait Implementations

impl Module for TransformerEncoderLayer

fn forward(&self, input: &Variable) -> Variable

Performs the forward pass.

fn parameters(&self) -> Vec<Parameter>

Returns all parameters of this module.

fn named_parameters(&self) -> HashMap<String, Parameter>

Returns named parameters of this module.

fn name(&self) -> &'static str

Returns the module name for debugging.

fn num_parameters(&self) -> usize

Returns the number of trainable parameters.

fn train(&mut self)

Sets the module to training mode.

fn eval(&mut self)

Sets the module to evaluation mode.

fn set_training(&mut self, _training: bool)

Sets the training mode.

fn is_training(&self) -> bool

Returns whether the module is in training mode.

fn zero_grad(&self)

Zeros all gradients of parameters.

fn to_device(&self, device: Device)

Moves all parameters to the specified device.