Struct TransformerEncoder 

pub struct TransformerEncoder { /* private fields */ }

Stack of N TransformerEncoderLayers.

Shape

• Input: (N, S, E)
• Output: (N, S, E)

Implementations

impl TransformerEncoder

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

Creates a TransformerEncoder with the given number of layers (post-norm).

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

Creates a TransformerEncoder with configurable norm ordering.

With pre-norm, a final LayerNorm is always added after the last layer (required since pre-norm layers don’t normalize their output).

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

Creates a TransformerEncoder without final layer norm.

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

Forward pass with optional source mask.

pub fn num_layers(&self) -> usize

Returns the number of layers.

Trait Implementations

impl Module for TransformerEncoder

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.