Open fuyimin96 opened 1 year ago
Hi, thanks for your interest. Yes exactly, we only load the pretrained weights of the first 11 layers when feature fusion is enabled. The intuition behind is that the input distribution of the ff_last_layer and the pretraiend layer is quite different. Sorry, we didn't conduct the experients of loading all the 12 layers weights. Loading the pretrained norm weights give slightly worser results on some datasets if I remember correctly.
Thanks for your reply