braindecode.modules.InceptionBlock#

class braindecode.modules.InceptionBlock(branches)[source]#

Inception block module.

This module applies multiple convolutional branches to the input and concatenates their outputs along the channel dimension. Each branch can have a different configuration, allowing the model to capture multi-scale features.

Parameters:

branches (list of nn.Module) – List of convolutional branches to apply to the input.

Methods

forward(x)[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.