Struct Rnn

pub struct Rnn {
    pub non_linearity: Arc<NonLinearity>,
    pub wxh: Param<Array>,
    pub whh: Param<Array>,
    pub bias: Param<Option<Array>>,
}

An Elman recurrent layer.

The input is a sequence of shape NLD or LD where:

• N is the optional batch dimension
• L is the sequence length
• D is the input’s feature dimension

The hidden state h has shape NH or H, depending on whether the input is batched or not. Returns the hidden state at each time step, of shape NLH or LH.

Fields

non_linearity: Arc<NonLinearity>

non-linearity function to use

wxh: Param<Array>

Wxh

whh: Param<Array>

Whh

bias: Param<Option<Array>>

Bias. Enabled by default.

Implementations

impl Rnn

pub fn new( input_size: impl Into<i32>, hidden_size: impl Into<i32>, ) -> Result<Self, <<Self as Buildable>::Builder as Builder<Self>>::Error>

Creates a new instance of Rnn.

impl Rnn

pub const DEFAULT_BIAS: bool = true

Default value for bias

pub const DEFAULT_NONLINEARITY: Option<Arc<NonLinearity>> = None

RnnBuilder::non_linearity is initialized with None, and the default non-linearity is tanh if not set.

pub fn step( &mut self, x: &Array, hidden: Option<&Array>, ) -> Result<Array, Exception>

Apply a single step of the RNN.

Trait Implementations

impl Buildable for Rnn

type Builder = RnnBuilder

The builder type for this buildable type

impl Builder<Rnn> for RnnBuilder

type Error = Exception

Error with building

fn build(self) -> Result<Rnn, Self::Error>

Build the type

impl Clone for Rnn

fn clone(&self) -> Rnn

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for Rnn

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

Formats the value using the given formatter.

impl<'a, Input> Module<Input> for Rnn

where Input: Into<RnnInput<'a>>,

type Error = Exception

Error type for the module.

type Output = Array

Output type of the module.

fn forward(&mut self, input: Input) -> Result<Array, Exception>

Forward pass of the module.

fn training_mode(&mut self, _mode: bool)

Set whether the module is in training mode.

impl ModuleParameters for Rnn

fn freeze_parameters(&mut self, recursive: bool)

Freeze all parameters in the module.

fn unfreeze_parameters(&mut self, recursive: bool)

Unfreeze all parameters in the module.

fn parameters(&self) -> ModuleParamRef<'_>

Get references to the module parameters.

fn parameters_mut(&mut self) -> ModuleParamMut<'_>

Get mutable references to the module parameters.

fn trainable_parameters(&self) -> ModuleParamRef<'_>

Get references to the trainable parameters. A parameter is trainable if it is NOT frozen.

fn all_frozen(&self) -> Option<bool>

Check if all parameters in the module are frozen. Returns None if there are no parameters.

fn any_frozen(&self) -> Option<bool>

Check if any parameter in the module is frozen. Returns None if there are no parameters.

fn update(&mut self, parameters: ModuleParam)

Update the module parameters.

fn update_flattened(&mut self, flattened_parameters: FlattenedModuleParam)

Update the module parameters from a flattened representation.