You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Such a two-stream sampling strategy is only used for semi-supervised settings (a batch contains labeled and unlabeled data at the same time). You don't have any unlabeled data in your scenario, so just using the original sampling strategy of pytorch is fine.
Sorry to raise issues again.
When I try to train the Vnet with all 80 labels, I get this error message:
The reason is that zero is passed to the init function of TwoStreamBatchSampler class. Am I using the wrong method to train the model?
The text was updated successfully, but these errors were encountered: