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
Hi @Macro03, thanks for your interest in our work.
In our implementation, the LR images are generated online during training thus you can safely remove self.dir_lr.
I trained the Moco by the two real world images instead of 'degrade' images, the contrast_loss increase in early epoch and then decrease slowly. What do you think of it? Thank you so munch!
Hi @Macro03, we also have this observation in our experiments on synthetic images. In my opinion, at early epochs, the random samples in the queue is gradually replaced with the training data. Thus, it becomes more difficult to distinguish positive samples from negative samples and the loss is increased. After a few epochs, the queue is completely replaced by the training data and the loss begins to decrease.
Hello, thank you very much for your excellent work. Does the trainning data only need HR images? Can I delete the self.dir_lr in df2k.py ?
The text was updated successfully, but these errors were encountered: