Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

run_iterationRAW parameter #2

Open
mhmd-mst opened this issue Jun 3, 2022 · 1 comment
Open

run_iterationRAW parameter #2

mhmd-mst opened this issue Jun 3, 2022 · 1 comment

Comments

@mhmd-mst
Copy link

mhmd-mst commented Jun 3, 2022

Hey,
I am trying to apply the techniques you proposed, I want to ask you regarding run_iterationRAW has parameter data_generatorRAW, what is the difference between it and data_generator?

@ZerojumpLine
Copy link
Owner

Hey,

Sorry for the delayed reply and thank you very much for your interests!
data_generatorRAW: it would give data with the original format, without any data augmentation.
data_generator: it is from default nnunet code, data with built-in data augmentation.
I would use data_generatorRAW to generate our version of transformed samples (w/ mixup and w/ adversarial training). Because I found the tranformed data w/ data_generator would be unstable as it becomes quite different from the original data.

Hope it can resolve your problem!

Best,
Zeju

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants