Closed imcjx closed 2 years ago
Hi, drop_path is very important and is loaded into the model (you can try to print the drop_path), and clip_grad is only active in the base size model.
imcjx @.***> 于2022年4月30日周六 17:45写道:
Thank you very much for your work. Is the parameters drop_path and clip_grad in the configuration file useless? they don't seem to be loaded into the model.
— Reply to this email directly, view it on GitHub https://github.com/OliverRensu/Shunted-Transformer/issues/6, or unsubscribe https://github.com/notifications/unsubscribe-auth/ANP7CCGOXBNYS63DGLVVUTTVHT6LTANCNFSM5UYD2ZGQ . You are receiving this because you are subscribed to this thread.Message ID: @.***>
Thank you very much for your work. Is the parameters
drop_path
andclip_grad
in the configuration file useless? they don't seem to be loaded into the model.