Repeat#

class sinabs.layers.Repeat(module: torch.nn.modules.module.Module)[source]#

Utility layer which wraps any nn.Module. It flattens time and batch dimensions of the input before feeding it to the child module and unflattens those dimensions to the original shape before passing it to the next layer.

Parameters

module (torch.nn.modules.module.Module) –

forward(x)[source]#

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.