1
$\begingroup$

Consider the following explanations regarding a batch normalization layers in PyTorch

#1: one dimensional batch normalization

class torch.nn.BatchNorm1d(.........)

Applies Batch Normalization over a 2D or 3D input (a mini-batch of 1D inputs with optional additional channel dimension)............

#2: Second dimensional batch normalization

class torch.nn.BatchNorm2d(..........)

Applies Batch Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension)

#3: Third dimensional batch normalization

class torch.nn.BatchNorm3d(..............)

Applies Batch Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension)

All these says that there can be extra element to each vector undergoing batch normalization and is related to channel.

Is the channel referred here same as the channels of image? If yes, then what it contains? Does it contains the number of channels in that particular layer?

Else, what does this additional channel contain?.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.