myinfo

Before proto

1

Hi! Sorry, i have too many questions bother you.... ``` class LTA(nn.Module): def forward(self, *input): elif type == 'proto_adapt': unseen_protos, seen_y = input[:-1] device = unseen_protos.device before_protos = torch.zeros(len(self.seen_class_protos), self.emb_size).to(device)...

Not init R

1

HI! Just a little question: For your paper: w / o Init" refers to the model that randomly initializes R rather than pretrained prototypes. But In code is S. Probably,...

Seen_N in train

3

Hi, nice work! I have read code, and i have a question. In batch sampler, i see we actual use remain classes as seen class , why not use seen_N?...

Pretraining accuracy for retromae v1

2

Great job! Hello , i wonder if you can tell me the training mlm accuracy of encoder and decoder. Im training my retromae model now.