# TotalSegmentator fails with error 120

**URL:** <https://discourse.slicer.org/t/totalsegmentator-fails-with-error-120/27130>\
**Category:** Support\
**Tags:** segmentation, ai\
**Created:** [January 9, 2023, 5:49am UTC](https://discourse.slicer.org/t/totalsegmentator-fails-with-error-120/27130 "2023-01-09T05:49:40Z")\
**Posts on this page:** 1\
**Showing post:** 4

<div class="post-metadata">

**Author:** ![lassoan](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/lassoan/32/13_2.png) [@lassoan](https://discourse.slicer.org/u/lassoan)\
**Post date:** [January 11, 2023, 3:11am UTC](https://discourse.slicer.org/t/totalsegmentator-fails-with-error-120/27130/4 "2023-01-11T03:11:19Z")

</div>

> [@LipTeck\_Chew](#):
>
> FileNotFoundError: [Errno 2] No such file or directory: ‘/home/lipteck/.totalsegmentator/nnunet/results/nnUNet/3d\_fullres/Task252\_TotalSegmentator\_part2\_vertebrae\_1139subj/nnUNetTrainerV2\_ep4000\_nomirror\_\_nnUNetPlansv2.1/fold\_0/model\_final\_checkpoint.model.pkl’

It seems that your model files download was incomplete, either due to some transient network issues or the download was interrupted.

You need to erase the /home/lipteck/.totalsegmentator/ folder and start again.

> [@LipTeck\_Chew](#):
>
> No GPU detected. Running on CPU. This can be very slow.

This indicates that there is an issue with your CUDA installation. Currently, pytorch supports CUDA 11.6 and 11.7 on Linux, for best compatibility install one of these CUDA versions. Then check if CUDA version shown in PyTorchUtils module in Slicer matches the installed CUDA version.

---

_[View the full topic](https://discourse.slicer.org/t/totalsegmentator-fails-with-error-120/27130)._