Can someone explain when to use BatchNorm1d
and when BatchNorm2d
?
From here BN1d is called temporal:
Because the Batch Normalization is done over the C dimension, computing statistics on (N, L) slices, it’s common terminology to call this Temporal Batch Normalization.
From here BN2d is called spatial:
Because the Batch Normalization is done over the C dimension, computing statistics on (N, H, W) slices, it’s common terminology to call this Spatial Batch Normalization.