Struct TransformerDecoder 

pub struct TransformerDecoder { /* private fields */ }

Stack of Transformer decoder layers.

Implementations

impl TransformerDecoder

pub fn new( d_model: usize, nhead: usize, num_layers: usize, dim_feedforward: usize, dropout: f32, ) -> Self

Create decoder with specified layers.

pub fn forward_with_memory( &self, tgt: &Variable, memory: &Variable, tgt_mask: Option<&Variable>, memory_mask: Option<&Variable>, ) -> Variable

Forward with memory and masks.

Trait Implementations

impl Module for TransformerDecoder

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

Performs the forward pass.

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

Returns all parameters of this module.

fn train(&mut self)

Sets the module to training mode.

fn eval(&mut self)

Sets the module to evaluation mode.

fn is_training(&self) -> bool

Returns whether the module is in training mode.

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

Returns named parameters of this module.

fn num_parameters(&self) -> usize

Returns the number of trainable parameters.

fn set_training(&mut self, _training: bool)

Sets the training mode.

fn zero_grad(&self)

Zeros all gradients of parameters.

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

Returns the module name for debugging.