braindecode.modules.LinearWithConstraint

class braindecode.modules.LinearWithConstraint(*args, max_norm=1.0, **kwargs)

Linear layer with max-norm constraint on the weights.

Examples

>>> import torch
>>> from braindecode.modules import LinearWithConstraint
>>> module = LinearWithConstraint(10, 5, max_norm=1.0)
>>> inputs = torch.randn(2, 10)
>>> outputs = module(inputs)
>>> outputs.shape
torch.Size([2, 5])