Struct BiRnn 

pub struct BiRnn<B>
where
    B: Backend,
{
    pub forward: Rnn<B>,
    pub reverse: Rnn<B>,
    pub d_hidden: usize,
    pub batch_first: bool,
}

The BiRnn module. This implementation is for Bidirectional RNN. Should be created with BiRnnConfig.

Fields

forward: Rnn<B>

RNN for the forward direction.

reverse: Rnn<B>

RNN for the reverse direction.

d_hidden: usize

The size of the hidden state.

batch_first: bool

If true, input is [batch_size, seq_length, input_size]. If false, input is [seq_length, batch_size, input_size].

Implementations

impl<B> BiRnn<B>

where B: Backend,

pub fn forward( &self, batched_input: Tensor<B, 3>, state: Option<RnnState<B, 3>>, ) -> (Tensor<B, 3>, RnnState<B, 3>)

Applies the forward pass on the input tensor. This Bidirectional RNN implementation returns the state for each element in a sequence (i.e., across seq_length) and a final state.

Parameters:

• batched_input: The input tensor of shape:
  • [batch_size, sequence_length, input_size] if batch_first is true (default)
  • [sequence_length, batch_size, input_size] if batch_first is false
• state: An optional RnnState representing the hidden state. Each state tensor has shape [2, batch_size, hidden_size]. If no initial state is provided, these tensors are initialized to zeros.

Returns:

• output: A tensor represents the output features of RNN. Shape:
  • [batch_size, sequence_length, hidden_size * 2] if batch_first is true
  • [sequence_length, batch_size, hidden_size * 2] if batch_first is false
• state: A RnnState represents the final forward and reverse states. The state.hidden have the shape [2, batch_size, hidden_size].

Trait Implementations

impl<B> AutodiffModule<B> for BiRnn<B>

where B: Backend + AutodiffBackend, <B as AutodiffBackend>::InnerBackend: Backend,

type InnerModule = BiRnn<<B as AutodiffBackend>::InnerBackend>

Inner module without auto-differentiation.

fn valid(&self) -> <BiRnn<B> as AutodiffModule<B>>::InnerModule

Returns the same module, but on the inner backend without auto-differentiation.

fn from_inner(module: <BiRnn<B> as AutodiffModule<B>>::InnerModule) -> BiRnn<B>

Wraps an inner module back into an auto-diff module.

impl<B> Clone for BiRnn<B>

where B: Backend,

fn clone(&self) -> BiRnn<B>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<B> Debug for BiRnn<B>

where B: Debug + Backend,

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

Formats the value using the given formatter.

impl<B> Display for BiRnn<B>

where B: Backend,

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

Formats the value using the given formatter.

impl<B> HasAutodiffModule<B> for BiRnn<<B as AutodiffBackend>::InnerBackend>

where B: Backend + AutodiffBackend, <B as AutodiffBackend>::InnerBackend: Backend,

type TrainModule = BiRnn<B>

The module with auto-differentiation.

impl<B> Module<B> for BiRnn<B>

where B: Backend,

type Record = BiRnnRecord<B>

Type to save and load the module.

fn load_record(self, record: <BiRnn<B> as Module<B>>::Record) -> BiRnn<B>

Load the module state from a record.

fn into_record(self) -> <BiRnn<B> as Module<B>>::Record

Convert the module into a record containing the state.

fn num_params(&self) -> usize

Get the number of parameters the module has, including all of its sub-modules.

fn visit<Visitor>(&self, visitor: &mut Visitor)

where Visitor: ModuleVisitor<B>,

Visit each tensor parameter in the module with a visitor.

fn map<Mapper>(self, mapper: &mut Mapper) -> BiRnn<B>

where Mapper: ModuleMapper<B>,

Map each tensor parameter in the module with a mapper.

fn collect_devices( &self, devices: Vec<<B as BackendTypes>::Device>, ) -> Vec<<B as BackendTypes>::Device>

Return all the devices found in the underneath module tree added to the given vector without duplicates.

fn to_device(self, device: &<B as BackendTypes>::Device) -> BiRnn<B>

Move the module and all of its sub-modules to the given device.

fn fork(self, device: &<B as BackendTypes>::Device) -> BiRnn<B>

Fork the module and all of its sub-modules to the given device.

fn devices(&self) -> Vec<<B as BackendTypes>::Device>

Return all the devices found in the underneath module tree without duplicates.

fn no_grad(self) -> Self

Each tensor in the module tree will not require grad.

fn train<AB>(self) -> Self::TrainModule

where AB: AutodiffBackend<InnerBackend = B>, Self: HasAutodiffModule<AB>,

Move the module and all of its sub-modules to the autodiff backend.

fn save_file<FR, PB>( self, file_path: PB, recorder: &FR, ) -> Result<(), RecorderError>

where FR: FileRecorder<B>, PB: Into<PathBuf>,

Save the module to a file using the provided file recorder.

fn load_file<FR, PB>( self, file_path: PB, recorder: &FR, device: &<B as BackendTypes>::Device, ) -> Result<Self, RecorderError>

where FR: FileRecorder<B>, PB: Into<PathBuf>,

Load the module from a file using the provided file recorder.

fn quantize_weights(self, quantizer: &mut Quantizer) -> Self

Quantize the weights of the module.

impl<B> ModuleDisplay for BiRnn<B>

where B: Backend,

fn custom_settings(&self) -> Option<DisplaySettings>

Custom display settings for the module.

fn custom_content(&self, content: Content) -> Option<Content>

Custom attributes for the module.

fn format(&self, passed_settings: DisplaySettings) -> String

Formats the module with provided display settings.

impl<B> ModuleDisplayDefault for BiRnn<B>

where B: Backend,

fn content(&self, content: Content) -> Option<Content>

Attributes of the module used for display purposes.

fn num_params(&self) -> usize

Gets the number of the parameters of the module.