You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, your work is really inspiring and interesting!
I am wondering why you re-implement LayerNorm (2D), instead of using PyTorch modules like nn.GroupNorm(1, channels)?
Are there some differences between them (e.g. final performance or function differences)?
The text was updated successfully, but these errors were encountered:
Hi, your work is really inspiring and interesting!
I am wondering why you re-implement LayerNorm (2D), instead of using PyTorch modules like
nn.GroupNorm(1, channels)
?Are there some differences between them (e.g. final performance or function differences)?
The text was updated successfully, but these errors were encountered: