braindecode.functional.glorot_weight_zero_bias

braindecode.functional.glorot_weight_zero_bias(model)

Set the weights of BatchNorm layers to one and all biases to zero.

Despite its name, this function does not apply the Glorot (Xavier) initialization: other weights keep the initialization of their layer (PyTorch’s default, or Xavier uniform for the max-norm constrained layers such as braindecode.modules.Conv2dWithConstraint). The name is kept for backward compatibility.

Parameters:

model (Module)