Jakob Wasserthal
Jakob Wasserthal
Unfortunately I am not familiar with windows details. My test installation on windows is working.
Great that it works now! Maybe 3d Slicer is using your GPU (if you have one) or it is using the `--fast` option or the `--roi_subset` option ?
Thanks for the report. On Linux and Mac this error does not occur therefore I do not really want to not allow pytorch 2.4 for those users. But it will...
The preprocessing is rather simple. TotalSegmentator resamples the images to 1.5mm isotropic resolution, then the images go to nnU-Net. nnU-Net will normalise the images, if I remember correctly to mean...
If you can share one of your datasets with me I can try to reproduce the issue. Otherwise it is difficult to say what the problem might be.
For this dataset it should work well. You do not need any of this code. Just get one of the nifti files and then run `TotalSegmentator -i your_downloaded_file.nii.gz -o segmentations...
Unfortunately I have no idea what the reason might be.
In 3D Slicer this is not possible. You can run it directly on the command line without 3D Slicer and write your own Bash script to combine the calls. However,...
TotalSegmentator is using the default nnU-Net. Please check their documentation for more details (https://github.com/MIC-DKFZ/nnUNet).
Unfortunately this error does not seem familiar to me. I guess it is related to Amazon SageMaker.