Struct GRU 

pub struct GRU<F: Float + Debug> { /* private fields */ }

Gated Recurrent Unit (GRU) layer

Implements a GRU layer with the following update rules: r_t = sigmoid(W_ir * x_t + b_ir + W_hr * h_(t-1) + b_hr) # reset gate z_t = sigmoid(W_iz * x_t + b_iz + W_hz * h_(t-1) + b_hz) # update gate n_t = tanh(W_in * x_t + b_in + r_t * (W_hn * h_(t-1) + b_hn)) # new gate h_t = (1 - z_t) * n_t + z_t * h_(t-1) # hidden state

Examples

use scirs2_neural::layers::{Layer, recurrent::GRU};
use scirs2_core::ndarray::{Array, Array3};
use scirs2_core::random::rngs::StdRng;
use scirs2_core::random::SeedableRng;
// Create a GRU layer with 10 input features and 20 hidden units
let mut rng = StdRng::seed_from_u64(42);
let gru = GRU::new(10, 20, &mut rng).unwrap();
// Forward pass with a batch of 2 samples, sequence length 5, and 10 features
let batch_size = 2;
let seq_len = 5;
let input_size = 10;
let input = Array3::<f64>::from_elem((batch_size, seq_len, input_size), 0.1).into_dyn();
let output = gru.forward(&input).unwrap();
// Output should have dimensions [batch_size, seq_len, hidden_size]
assert_eq!(output.shape(), &[batch_size, seq_len, 20]);

Implementations

impl<F: Float + Debug + ScalarOperand + 'static> GRU<F>

pub fn new<R: Rng + RngCore>( input_size: usize, hidden_size: usize, rng: &mut R, ) -> Result<Self>

Create a new GRU layer

Arguments

• input_size - Number of input features
• hidden_size - Number of hidden units
• rng - Random number generator for weight initialization

Returns

• A new GRU layer

Trait Implementations

impl<F: Float + Debug + ScalarOperand + Send + Sync + 'static> Layer<F> for GRU<F>

fn as_any(&self) -> &dyn Any

Get the layer as a dyn Any for downcasting

fn as_any_mut(&mut self) -> &mut dyn Any

Get the layer as a mutable dyn Any for downcasting

fn forward(&self, input: &Array<F, IxDyn>) -> Result<Array<F, IxDyn>>

Forward pass of the layer

fn backward( &self, input: &Array<F, IxDyn>, _grad_output: &Array<F, IxDyn>, ) -> Result<Array<F, IxDyn>>

Backward pass of the layer to compute gradients

fn update(&mut self, learningrate: F) -> Result<()>

Update the layer parameters with the given learning rate

fn params(&self) -> Vec<Array<F, IxDyn>>

Get the parameters of the layer

fn gradients(&self) -> Vec<Array<F, IxDyn>>

Get the gradients of the layer parameters

fn set_gradients(&mut self, _gradients: &[Array<F, IxDyn>]) -> Result<()>

Set the gradients of the layer parameters

fn set_params(&mut self, _params: &[Array<F, IxDyn>]) -> Result<()>

Set the parameters of the layer

fn set_training(&mut self, _training: bool)

Set the layer to training mode (true) or evaluation mode (false)

fn is_training(&self) -> bool

Get the current training mode

fn layer_type(&self) -> &str

Get the type of the layer (e.g., “Dense”, “Conv2D”)

fn parameter_count(&self) -> usize

Get the number of trainable parameters in this layer

fn layer_description(&self) -> String

Get a detailed description of this layer

fn inputshape(&self) -> Option<Vec<usize>>

Get the input shape if known

fn outputshape(&self) -> Option<Vec<usize>>

Get the output shape if known

fn name(&self) -> Option<&str>

Get the name of the layer if set

impl<F: Float + Debug + ScalarOperand + Send + Sync + 'static> ParamLayer<F> for GRU<F>

fn get_parameters(&self) -> Vec<Array<F, IxDyn>>

Get the parameters of the layer as a vector of arrays

fn get_gradients(&self) -> Vec<Array<F, IxDyn>>

Get the gradients of the parameters

fn set_parameters(&mut self, params: Vec<Array<F, IxDyn>>) -> Result<()>

Set the parameters