Giters

MIC-DKFZ / nnDetection

nnDetection is a self-configuring framework for 3D (volumetric) medical object detection which can be applied to new data sets without manual intervention. It includes guides for 12 data sets that were used to develop and evaluate the performance of the proposed method.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[Question]About loss

alonelysnake opened this issue · comments

commented

❓ Question

In my task, I found the train loss<=0 after several epochs. What caused this problem? Should I continue to train the model?

commented

Yes, simply continue the training, it is normal that the loss becomes negative at some points. While most losses in nnDetection are positive, we simply use -GIoU as the loss instead of 1-GIoU to avoid unnecessary computations - the optimization target remains the same in both cases.

commented

This issue is stale because it has been open for 30 days with no activity.

commented

This issue was closed because it has been inactive for 14 days since being marked as stale.