Ole Johannsen

Did using the most recent version help? If so, I will close the issue.

Hey, could you please provide more information? What do you mean by 3 or 4 frames? cases/images? channels? What brings you to the conclusion that it might originate form SimpleITK...

Hey, I'm using version 1.0.6 provided through pypi. I can try the current repro version. I used the code you provided to compute the "JI vs IoU matching threshold" plot....

Could you give me the commands you used? Did you setup your environment variables correctly? See https://github.com/MIC-DKFZ/nnUNet/blob/2d2e8ce2c0261dc88b53866dcc4c71e6972432ed/documentation/setting_up_paths.md

hey, just to make sure. does it work if you do not use any pre-trained weights? did you follow the instructions here https://github.com/MIC-DKFZ/nnUNet/blob/master/documentation/pretraining_and_finetuning.md ?

thanks for the inquiry, I will forward this to Fabian.

as this is a very specific file format with not much use Fabian suggests that you create a fork on your end and add the support to the file format.

did you resolve the problem by now? to me it looks like there is a problem with the data. with nibeal, do you mean nibabel? as everthing in the dataset_properties.pkl...

are the corresponding files present in /nnUNet_results/Dataset101_SEL/nnUNetTrainer__nnUNetPlans__3d_fullres ? maybe its a problem with the respective folders?

just to make sure, you are still talking about labels for segmentation? nnU-Net will use its own data format internally for performance reasons. Thus, I do not believe that this...