-
Notifications
You must be signed in to change notification settings - Fork 25
Open
Description
Hello,I'm trying to use my own private dataset of lung CT images.However,during the MedLAM stage,the predicted values and the true values differ significantly,and the Dice coefficient is not high either.I've tried tuning the parameters but to no avail.I was wondering if there's anything I might have overlooked in the data preprocessing stage of your dataset,or if you have any solutions.Thank you very much!
Metadata
Metadata
Assignees
Labels
No labels