grelu.model.trunks.explainn

Classes

ExplaiNNConvBlock	Convolutional block for the ExplaiNN model.
ExplaiNNTrunk	The ExplaiNN model architecture.

Module Contents

class grelu.model.trunks.explainn.ExplaiNNConvBlock(in_channels: int, out_channels: int, kernel_size: int, groups: int, act_func: str, dropout: float, dtype=None, device=None)

Bases: torch.nn.Module

Convolutional block for the ExplaiNN model.

Parameters:

• in_channels – Number of input channels

• out_channels – Number of output channels

• kernel_size – Width of the convolutional kernel

• groups – Number of groups for the convolutional layer

• act_func – Activation function

• dropout – Dropout rate

• dtype – Data type for the layers.

• device – Device for the layers.

conv

norm

act

dropout

pool

flatten

forward(x: torch.Tensor) → torch.Tensor

Forward pass

Parameters:

x – Input tensor of shape (N, C, L)

Returns:

Output tensor

class grelu.model.trunks.explainn.ExplaiNNTrunk(in_len: int, channels=300, kernel_size=19, dtype=None, device=None)

Bases: torch.nn.Module

The ExplaiNN model architecture.

Parameters:

• n_tasks (int) – number of outputs

• input_length (int) – length of the input sequences

• channels (int) – number of independent CNN units (default=300)

• kernel_size (int) – size of each unit’s conv. filter (default=19)

• dtype – Data type for the layers.

• device – Device for the layers.

channels

blocks

forward(x: torch.Tensor) → torch.Tensor

Forward pass

Parameters:

x – Input tensor of shape (N, C, L)

Returns:

Output tensor