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
Thanks for updating the implementation frequently! The codebase looks much nicer than when I first looked at it. I took a closer look on the details and would like to ask some questions on specific design choice. Of course I understand that not every specific design comes with a reason, but I would like to know if you have reference/intuition on these things:
It seems like in the main generator, self attention comes before cross attention, while in the upsampler, cross attention comes before self attention.
This line has a residual connection, but it is already done inside the Transformer class. Same here. Is this something new in transformer literature?
Here in the discriminator, the residual is added after attention block. Does it make more sense to add it right after two conv blocks, since the attention block has its own residual connection?
Very tiny issue. The definition in this is unused.
The text was updated successfully, but these errors were encountered:
Thanks for updating the implementation frequently! The codebase looks much nicer than when I first looked at it. I took a closer look on the details and would like to ask some questions on specific design choice. Of course I understand that not every specific design comes with a reason, but I would like to know if you have reference/intuition on these things:
The text was updated successfully, but these errors were encountered: