I think the use of 't_label' is forbidden for unsupervised learning tasks when training.
chihuadelishu opened this issue · comments
Why do you use the labels of target domain (i.e. t_label) to calculate loss during training models?I think the use of 't_label' is forbidden for unsupervised learning tasks.
PS: .\trainer\dcc1_trainer.py:
class Trainer(BaseTrainer):
def iter(self, i_iter):
......
en_loss = self.memory.forward(t_feat, t_label, self.config.t, False)
Hello,
We did not use the ground truth of target samples, the t_label you mentioned is the pseudo label that obtained through clustering. For details, you can refer to
Thanks for your prompt reply. It is my negligence. :)