Flux model corresponding to PyTorch nn.BatchNorm1d

Flux provides several different normalization “models” to model normalization layers. Which one of them corresponds to the PyTorch’s nn.BatchNorm1d?

Flux.BatchNorm can be used in place of nn.BatchNorm1d, nn.BatchNorm2d, nn.BatchNorm3d

But PyTorch has an affine:bool keyword option in its nn.BatchNorm1d. As far as I can tell, Flux.BatchNorm doesn’t have that option. Is it implicitly true in Flux?

was just not documented up to a few days ago Adds affine and track_stats params to BatchNorm docstring by Mottl · Pull Request #1729 · FluxML/Flux.jl · GitHub

Ah nice. Thanks!