models.generator.BackboneGen

class BackboneGen(cfg: BaseConfig, in_channels: int = 2, init_weights: bool = True)

Bases: ModelGen

Model base generator

Returns the tensor from the last layer of the network.

Parameters:

• cfg (BaseConfig) – Network Configuration Generator.

• in_channels (int, optional) – Number of input channels. Defaults to 2.

• init_weights (bool, optional) – If true apply weight initialization function. Defaults to True.

Methods

forward	Network pass for data containing time resolution
forward_impl	State-based network pass

Attributes

training

forward(X: Tensor) → Tensor

Network pass for data containing time resolution

Parameters:

X (torch.Tensor) – Input tensor. Shape is Shape [ts, batch, channel, h, w].

Returns:

The resulting tensor and the list of new states.

Return type:

torch.Tensor,

forward_impl(X: Tensor, state: ListState | None) → Tuple[Tensor, ListState]

State-based network pass

Parameters:

• X (torch.Tensor) – Input tensor. Shape is Shape [batch, channel, h, w].

• state (ListState | None, optional) – List of block layer states. Defaults to None.

Returns:

The resulting tensor and the list of new states.

Return type:

Tuple[torch.Tensor, ListState]