Struct burn_core::nn::lstm::Lstm

pub struct Lstm<B: Backend> { /* private fields */ }

The Lstm module. This implementation is for a unidirectional, stateless, Lstm.

Implementations

impl<B: Backend> Lstm<B>

pub fn forward( &self, batched_input: Tensor<B, 3>, state: Option<(Tensor<B, 2>, Tensor<B, 2>)> ) -> (Tensor<B, 3>, Tensor<B, 3>)

Applies the forward pass on the input tensor. This LSTM implementation returns the cell state and hidden state for each element in a sequence (i.e., across seq_length), producing 3-dimensional tensors where the dimensions represent [batch_size, sequence_length, hidden_size].

Parameters: batched_input: The input tensor of shape [batch_size, sequence_length, input_size]. state: An optional tuple of tensors representing the initial cell state and hidden state. Each state tensor has shape [batch_size, hidden_size]. If no initial state is provided, these tensors are initialized to zeros.

Returns: A tuple of tensors, where the first tensor represents the cell states and the second tensor represents the hidden states for each sequence element. Both output tensors have the shape [batch_size, sequence_length, hidden_size].

Trait Implementations

impl<B> ADModule<B> for Lstm<B>where B: ADBackend + Backend, <B as ADBackend>::InnerBackend: Backend,

type InnerModule = Lstm<<B as ADBackend>::InnerBackend>

Inner module without auto-differentiation.

fn valid(&self) -> Self::InnerModule

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

impl<B: Backend> Clone for Lstm<B>

fn clone(&self) -> Self

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<B: Debug + Backend> Debug for Lstm<B>

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

Formats the value using the given formatter.

impl<B: Backend> Display for Lstm<B>

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

Formats the value using the given formatter.

impl<B: Backend> Module<B> for Lstm<B>

type Record = LstmRecord<B>

Type to save and load the module.

fn load_record(self, record: Self::Record) -> Self

Load the module state from a record.

fn into_record(self) -> Self::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<V: ModuleVisitor<B>>(&self, visitor: &mut V)

Visit each tensor in the module with a visitor.

fn map<M: ModuleMapper<B>>(self, mapper: &mut M) -> Self

Map each tensor in the module with a mapper.

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

Get the device list of the module and all of its sub-modules.

fn fork(self, device: &B::Device) -> Self

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

fn to_device(self, device: &B::Device) -> Self

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

fn no_grad(self) -> Self

Each tensor in the module tree will not require grad.

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

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

fn load_file<FR: FileRecorder, PB: Into<PathBuf>>( self, file_path: PB, recorder: &FR ) -> Result<Self, RecorderError>

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