model.tools.generator.ResidualModule

model.tools.generator.ResidualModule#

class ResidualModule(mode: str, storage: Storage)[source]#

Bases: Module

The class combines data stored in the storage by summing or concatenating

It is used to create dense or residual networks.

Parameters:

  • mode (str) –

    Method of combining:

    • ”residual” - summarizes data

    • ”dense” - combines data across channels

  • storage (Storage) – Storage to merge

Methods

forward

Define the computation performed at every call.

Attributes

training

forward(X=None) → Tensor[source]#

Define 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.

Contents