about group normalization size

[alalbiol]

Hi
I am also implementing this algorithm and I want to check something with you...

I see that in your implementation you set the number of groups to 8:
num_groups=8
self.norm1 = nn.GroupNorm(num_groups=num_groups, num_channels=inChans)

But in the paper myronenko says literally:
GN stands for group normalization (with group size of 8)

so this can also understood that each group has 8 channels and therefore
num_groups = inChans/8

What do you think?