Struct LTC 

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

LTC RNN Layer

A full RNN layer that processes sequences using LTC cells. Supports batching, state management, mixed memory (LSTM), and variable timespans.

Type Parameters

• B - The backend type

Implementations

impl<B: Backend> LTC<B>

pub fn new(input_size: usize, wiring: impl Wiring, device: &B::Device) -> Self

Create a new LTC RNN layer with the given wiring

Arguments

• input_size - Number of input features
• wiring - Wiring configuration defining the network structure
• device - Device to create the module on

pub fn with_batch_first(self, batch_first: bool) -> Self

Set whether input is batch-first (default: true)

When true: input shape is [batch, seq, features] When false: input shape is [seq, batch, features]

pub fn with_return_sequences(self, return_sequences: bool) -> Self

Set whether to return full sequences (default: true)

When true: returns all timesteps [batch, seq, state_size] When false: returns only last timestep [batch, state_size]

pub fn with_mixed_memory(self, mixed_memory: bool, device: &B::Device) -> Self

Enable or disable mixed memory mode (LSTM augmentation)

When enabled, an LSTM cell processes the LTC output for better long-term memory. The LSTM cell is initialized when this is called with true.

Arguments

• mixed_memory - Whether to enable mixed memory mode
• device - Device to create the LSTM cell on (required when enabling)

pub fn input_size(&self) -> usize

Get input size

pub fn state_size(&self) -> usize

Get state size (number of neurons)

pub fn motor_size(&self) -> usize

Get motor/output size

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

Forward pass through the LTC RNN layer

Arguments

• input - Input tensor of shape:
  • 3D batched: [batch, seq, features] if batch_first=true
  • 3D batched: [seq, batch, features] if batch_first=false
  • 2D unbatched: [seq, features]
• state - Optional initial state tensor of shape [batch, state_size]
• timespans - Optional time intervals tensor of shape [batch, seq] or scalar

Returns

Tuple of (output, final_state) where:

• output: [batch, seq, motor_size] or [batch, motor_size] depending on return_sequences
• final_state: [batch, state_size] or ([batch, state_size], [batch, state_size]) for mixed_memory

pub fn forward_mixed( &self, input: Tensor<B, 3>, state: Option<(Tensor<B, 2>, Tensor<B, 2>)>, timespans: Option<Tensor<B, 2>>, ) -> (Tensor<B, 3>, (Tensor<B, 2>, Tensor<B, 2>))

where B: Backend,

Forward pass with mixed memory (LSTM augmentation)

This follows the Python implementation order: LSTM first (for memory), then LTC (for continuous-time dynamics).

This is only available when mixed_memory is enabled

Trait Implementations

impl<B> AutodiffModule<B> for LTC<B>

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

type InnerModule = LTC<<B as AutodiffBackend>::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 LTC<B>

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

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

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

Formats the value using the given formatter.

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

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

Formats the value using the given formatter.

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

type Record = LTCRecord<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<Visitor: ModuleVisitor<B>>(&self, visitor: &mut Visitor)

Visit each tensor parameter in the module with a visitor.

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

Map each tensor parameter in the module with a mapper.

fn collect_devices(&self, devices: Devices<B>) -> Devices<B>

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

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

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

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

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

fn devices(&self) -> Vec<<B as Backend>::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 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 Backend>::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<C>(self, quantizer: &mut Quantizer<C>) -> Self

where C: Calibration,

Quantize the weights of the module.

impl<B: Backend> ModuleDisplay for LTC<B>

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

Formats the module with provided display settings.

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.

impl<B: Backend> ModuleDisplayDefault for LTC<B>

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.