shredx.modules.rnn.GRUEncoder

class shredx.modules.rnn.GRUEncoder(input_size: int, hidden_size: int, num_layers: int, dropout: float, device: str = 'cpu', **kwargs)

Bases: Module

GRU encoder for sequence-to-sequence modeling.

Wraps PyTorch’s GRU with dropout and output reshaping for compatibility with encoder–decoder architectures.

Parameters:

input_sizeint

Input feature dimension.

hidden_sizeint

Hidden state dimension.

num_layersint

Number of stacked GRU layers.

dropoutfloat

Dropout probability applied to the outputs.

devicestr, optional

Device on which to place the module. Default is "cpu".

**kwargs

Additional keyword arguments passed for compatibility but ignored.

Methods

forward(x)

Apply the GRU encoder to an input batch.

Notes

Class Methods:

forward(x):

• Applies the GRU encoder to an input batch.

• Parameters:

  • x : Float[torch.Tensor, "batch sequence input_size"]. Input tensor.

• Returns:

  • tuple. Tuple containing the final output tensor of shape (batch_size, 1, 1, hidden_size) and None for no auxiliary losses.