Jakob Wasserthal
Jakob Wasserthal
Which version of nibabel are you using and which version of TractSeg?
Trackvis is no longer supported by nibabel. So you can not use the output format `trk_legacy`. The other output formats should work. Otherwise you can try doing `pip install --upgrade...
It seems that dipy does not work well with the older nibabel. I would recommend to not use `trk_legacy` output format, but `trk` or `tck`.
For the `total` task you can set the argument `--roi_subset brain` to only get the brain. This should also make it run faster.
You can manually download the weights using `totalseg_download_weights` on your local machine with internet. Then all weights will get downloaded to ~/.totalsegmentator. Then you can copy this folder to the...
The files need to be unzipped. But if you did this it is hard to say what the problem might without seeing your system.
Hi Henrik, there is indeed no real documentation about the training of this model. It was trained on two datasets: the totalsegmentator dataset but in addition on a high resolution...
Thanks for reporting this error. Unfortunately I can not reproduce it. For me it works with different DICOM files.
This is happening somewhere in the nnunet package. I will investigate that but might take some time. A fast solution would be to call TotalSegmentator from within python as a...
I committed a fix here: https://github.com/wasserth/TotalSegmentator/commit/1de45113756dad7c8d2d489fbc98a14d2e4c9f9a This is not in master yet. I will merge the branch when a few other features are ready.