torch.nn.GroupNorm関数の使い方

Question

https://pytorch.org/docs/master/generated/torch.nn.GroupNorm.html
では

>>> input = torch.randn(20, 6, 10, 10)
>>> # Separate 6 channels into 3 groups
>>> m = nn.GroupNorm(3, 6)
>>> # Separate 6 channels into 6 groups (equivalent with InstanceNorm)
>>> m = nn.GroupNorm(6, 6)
>>> # Put all 6 channels into a single group (equivalent with LayerNorm)
>>> m = nn.GroupNorm(1, 6)
>>> # Activating the module
>>> output = m(input)

と書いてありますがoutput = m(input)をどこで使えばいいかわかりません
CNN もしくはnn.Linearの代わりに使えばいいのですか？
わかる人教えてください