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
Hello, thank you for making your source code available; I wish to know why you've not implemented the PU, UIoU metrics and ECE loss function as stated in the paper. Are they not more important for a good training comparing to CategoricalCrossentropy loss and accuracy metric used here?
The text was updated successfully, but these errors were encountered:
Hello, thank you for making your source code available; I wish to know why you've not implemented the PU, UIoU metrics and ECE loss function as stated in the paper. Are they not more important for a good training comparing to CategoricalCrossentropy loss and accuracy metric used here?
The text was updated successfully, but these errors were encountered: