# What is an "additional channel dimension" contain in batch normalization?

Consider the following explanations regarding a batch normalization layers in PyTorch

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

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

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

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

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?.