a question about Warmup dataloader mode
jiangyangbo opened this issue · comments
yangbo jiang commented
in the process of warmup, the mode is 'all', it means it will take all the train data for training , and the train data include both
the labeled data and the unlabeled data, it may have some influence on the input of GMM, the unlabeled data with it's labled are trained in the process of warmup, what i say is right?
Junnan Li commented
hi, thanks for your interest!
Yes during warmup all data is used for training. The network is expected to learn something useful from all training data, such that it can produce high loss for noisy data when the GMM starts.