Jakob Wasserthal
Jakob Wasserthal
Thanks for sending the data. If you run the following commands, it works for me. ``` TractSeg -i dwi_b1000_MNI.nii.gz -o tractseg_output --raw_diffusion_input TractSeg -i tractseg_output/peaks.nii.gz -o tractseg_output --output_type endings_segmentation TractSeg...
I would try again on a different computer
The docker container seems to not work properly with `--raw_diffusion_input`. Use it without this option or run it without the docker container.
TotalSegmentator is using nnU-Net. The torch class is inside of nnU-Net. You will have investigate that library to find the torch class: https://github.com/MIC-DKFZ/nnUNet. The pretrained weights are in the releases:...
You need your own dataset for coronary arteries. Then you train a default nnU-Net following the default nnU-Net documentation.
I think the method `build_network_architecture` comes form nnU-Net. Have you installed nnUNet? Otherwise I am a bit clueless about this.
Can you send me the image then I can try to reproduce the issue?
Good questions! The data was resampled to 1.5mm, then the manuall annotation was done on these 1.5mm images. The evaluation is also done on these 1.5mm images then. For each...
> I was not sure if this was worth a separate issue, but I also wanted to ask about the training dataset. The Zenodo dataset does not have any metadata...
I see your points. Unfortunately, Zenodo seems to be quite slow sometimes. I agree, that uploading to a AWS bucket would be better. Then downloading the 28GB should also be...