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
If the pair_constraint = false, the code will use DatasetNoPair. Like DatasetPair, the DatasetNoPair also can call transform (RandomRot, RandomFlip). In paired mode, the cover and stego images will be both rotated or flipped using the same setting.
However, when in no-pair mode, it can rotate or flip the cover image only, the corresponding stego image may not be rotated or flipped. Because the DatasetNoPair only load one image once.
Therefore, if set pair_constraint = false, the only transforms.Compose([
utils.ToTensor()
]) can be used?
The text was updated successfully, but these errors were encountered:
I rotate and flip them the same way because it's just easier to do (it doesn't really matter there is no real dependencies between cover and stego when you use DatasetNoPair).
Statistically the data augmentation is the same (the probability of being flipped and rotate is the same whether it's a cover or a stego).
If the pair_constraint = false, the code will use DatasetNoPair. Like DatasetPair, the DatasetNoPair also can call transform (RandomRot, RandomFlip). In paired mode, the cover and stego images will be both rotated or flipped using the same setting.
However, when in no-pair mode, it can rotate or flip the cover image only, the corresponding stego image may not be rotated or flipped. Because the DatasetNoPair only load one image once.
Therefore, if set pair_constraint = false, the only transforms.Compose([
utils.ToTensor()
]) can be used?
The text was updated successfully, but these errors were encountered: