DentalSegmentator failed to load the segmentation

Support
,
1

Failed to load the segmentation.

Check the inference folder content C:\Users\Khateeb\AppData\Local\Temp\Slicer-iPdxkt\output

Operating system: windous 10
Slicer version:5.7 latest
Expected behavior:dentatl segmentator extension
Actual behavior:not working

2

SlicerDentalSegmentator developers, @Gauthier @Thibault_Pelletier, can you help with this issue?

Also see

3

Hi @karim_mamdouh,

Thank you for your interest in our extension.
Just a note : please avoid posting the same issue in different topics.

As mentioned in another topic, could you give us the log content when you experience this error?

The logs can be found by pressing the (i) button next to the apply button

image

4

Hello there!
Recently I have installed Slicer 5.7.0-2024-06-01 as well as the DentalSegmentation extension and tried to use it on sample data available through Slicer (CBCTDentalSurgery). However I encountered the same problem as Karim did: “Failed to load segmentation”.
@Gauthier @Thibault_Pelletier, I’d be grateful for any help as this extension seems to do a great job in dental segmentation.

OS: Win10
Slicer: Slicer 5.7.0-2024-06-01

The following is the log results:

Blockquote
2024/07/31 16:56:02.797 :: nnUNet is already installed (2.5.1) and compatible with requested version (nnunetv2).
2024/07/31 16:56:11.852 :: Transferring volume to nnUNet in C:/Users/Михалыч/AppData/Local/Temp/Slicer-GbtAsy
2024/07/31 16:56:14.722 :: Starting nnUNet with the following parameters:
2024/07/31 16:56:14.722 ::
2024/07/31 16:56:14.722 :: C:\ProgramData\slicer.org\Slicer 5.7.0-2024-06-01\lib\Python\Scripts\nnUNetv2_predict.exe -i C:/Users/Михалыч/AppData/Local/Temp/Slicer-GbtAsy/input -o C:/Users/Михалыч/AppData/Local/Temp/Slicer-GbtAsy/output -d Dataset111_453CT -tr nnUNetTrainer -p nnUNetPlans -c 3d_fullres -f 0 -npp 1 -nps 1 -step_size 0.5 -device cpu -chk checkpoint_final.pth --disable_tta
2024/07/31 16:56:14.722 ::
2024/07/31 16:56:14.722 :: JSON parameters :
2024/07/31 16:56:14.722 :: {
2024/07/31 16:56:14.722 :: “folds”: “0”,
2024/07/31 16:56:14.722 :: “device”: “cuda”,
2024/07/31 16:56:14.722 :: “stepSize”: 0.5,
2024/07/31 16:56:14.722 :: “disableTta”: true,
2024/07/31 16:56:14.722 :: “nProcessPreprocessing”: 1,
2024/07/31 16:56:14.722 :: “nProcessSegmentationExport”: 1,
2024/07/31 16:56:14.722 :: “checkPointName”: “”,
2024/07/31 16:56:14.722 :: “modelPath”: {
2024/07/31 16:56:14.722 :: "path": “C:\ProgramData\slicer.org\Slicer 5.7.0-2024-06-01\slicer.org\Extensions-32886\DentalSegmentator\lib\Slicer-5.7\qt-scripted-modules\Resources\ML”
2024/07/31 16:56:14.722 :: }
2024/07/31 16:56:14.722 :: }
2024/07/31 16:56:14.727 :: nnUNet preprocessing…
2024/07/31 16:56:22.286 :: C:\ProgramData\slicer.org\Slicer 5.7.0-2024-06-01\lib\Python\Lib\site-packages\nnunetv2\inference\predict_from_raw_data.py:84: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See pytorch/SECURITY.md at main · pytorch/pytorch · GitHub for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don’t have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
2024/07/31 16:56:22.286 :: checkpoint = torch.load(join(model_training_output_dir, f’fold{f}', checkpoint_name),
2024/07/31 16:56:24.111 :: C:\ProgramData\slicer.org\Slicer 5.7.0-2024-06-01\lib\Python\Lib\site-packages\nnunetv2\utilities\plans_handling\plans_handler.py:37: UserWarning: Detected old nnU-Net plans format. Attempting to reconstruct network architecture parameters. If this fails, rerun nnUNetv2_plan_experiment for your dataset. If you use a custom architecture, please downgrade nnU-Net to the version you implemented this or update your implementation + plans.
2024/07/31 16:56:24.111 :: warnings.warn("Detected old nnU-Net plans format. Attempting to reconstruct network architecture "
2024/07/31 16:56:35.836 :: Process SpawnProcess-16:
2024/07/31 16:56:35.849 :: Traceback (most recent call last):
2024/07/31 16:56:35.849 :: File “C:\ProgramData\slicer.org\Slicer 5.7.0-2024-06-01\lib\Python\Lib\runpy.py”, line 197, in _run_module_as_main
2024/07/31 16:56:36.016 :: #######################################################################
2024/07/31 16:56:36.016 :: Please cite the following paper when using nnU-Net:
2024/07/31 16:56:36.016 :: Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2), 203-211.
2024/07/31 16:56:36.016 :: #######################################################################
2024/07/31 16:56:36.016 ::
2024/07/31 16:56:36.016 :: perform_everything_on_device=True is only supported for cuda devices! Setting this to False
2024/07/31 16:56:36.016 :: There are 1 cases in the source folder
2024/07/31 16:56:36.016 :: I am process 0 out of 1 (max process ID is 0, we start counting with 0!)
2024/07/31 16:56:36.016 :: There are 1 cases that I would like to predict
2024/07/31 16:56:37.892 :: Loading inference results…
2024/07/31 17:02:45.830 :: Error loading results :
2024/07/31 17:02:45.830 :: Failed to load the segmentation.
2024/07/31 17:02:45.830 :: Check the inference folder content C:\Users\Михалыч\AppData\Local\Temp\Slicer-GbtAsy\output