Tassilo Wald
Tassilo Wald
Seems like @JackRio answered your question.
Hey jiashizuo, generally it is not recommended to train 2D models over 3D models (and 2D is generally always worse). That being said, I am not familiar with the 2D...
Closing this due to inactivity
I assume this answered your questions, hence I will close this issue. Feel free to re-open if necessary.
Is this issue still persisting?
Hey @tedi14 is this issue still persisting? If yes it would be great if you could post what the issue was and close this issue.
Breaking when the stopping criterion is hit should be sufficient. I am not sure if the `final_checkpoint.pth` is saved after the loop, but if not you can include it there...
Closing due to inactivity
You should raise these issues in batchgenerators (https://github.com/MIC-DKFZ/batchgenerators) as the issues originate from batchgenerators scipy imports.
Sorry for the late reply. Is the issue still persisting or did you fix the issue already? If you found the issue it would be great if you could share...