# Error While using 'Total Segmentator'

**URL:** <https://discourse.slicer.org/t/error-while-using-total-segmentator/26925>\
**Category:** Support\
**Created:** [December 26, 2022, 3:07pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925 "2022-12-26T15:07:32Z")\
**Posts on this page:** 20\
**Page:** 1

<div class="post-metadata">

**Author:** ![Dror1](https://avatars.discourse-cdn.com/v4/letter/d/d07c76/32.png) [@Dror1](https://discourse.slicer.org/u/Dror1)\
**Post date:** [December 26, 2022, 3:07pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/1 "2022-12-26T15:07:32Z")

</div>

hey all,

I’m having an error while trying to use the ‘total segmentator’ module.

Traceback (most recent call last):  
File “C:\Users\dror\AppData\Local\NA-MIC\Slicer 5.2.1\bin\Python\slicer\util.py”, line 2961, in tryWithErrorDisplay  
yield  
File “C:/Users/dror/AppData/Local/NA-MIC/Slicer 5.2.1/NA-MIC/Extensions-31317/TotalSegmentator/lib/Slicer-5.2/qt-scripted-modules/TotalSegmentator.py”, line 248, in onApplyButton  
self.logic.setupPythonRequirements()  
File “C:/Users/dror/AppData/Local/NA-MIC/Slicer 5.2.1/NA-MIC/Extensions-31317/TotalSegmentator/lib/Slicer-5.2/qt-scripted-modules/TotalSegmentator.py”, line 532, in setupPythonRequirements  
slicer.util.pip\_install(totalSegmentatorPackage + " --no-deps" + (" --upgrade" if upgrade else “”))  
File “C:\Users\dror\AppData\Local\NA-MIC\Slicer 5.2.1\bin\Python\slicer\util.py”, line 3571, in pip\_install  
\_executePythonModule(‘pip’, args)  
File “C:\Users\dror\AppData\Local\NA-MIC\Slicer 5.2.1\bin\Python\slicer\util.py”, line 3533, in \_executePythonModule  
logProcessOutput(proc)  
File “C:\Users\dror\AppData\Local\NA-MIC\Slicer 5.2.1\bin\Python\slicer\util.py”, line 3502, in logProcessOutput  
raise CalledProcessError(retcode, proc.args, output=proc.stdout, stderr=proc.stderr)  
subprocess.CalledProcessError: Command ‘[‘C:/Users/dror/AppData/Local/NA-MIC/Slicer 5.2.1/bin/…/bin\PythonSlicer.EXE’, ‘-m’, ‘pip’, ‘install’, ‘git+https://github.com/wasserth/TotalSegmentator.git’, ‘–no-deps’]’ returned non-zero exit status 1.

Does anyone know how to fix it?

---

<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:** [December 26, 2022, 3:25pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/2 "2022-12-26T15:25:25Z")

</div>

Totalsegmentator is downloaded using git (revision control tool), therefore you need to have git installed on your system. If you update the extension to the latest version then it automatically offers to install it. If this does not work for you for any reason then you can install git manually from [here](https://git-scm.com/download). After git installation, restart your computer and TotalSegmentator installation should succeed. If there is still problem then let me know and I send further instructions.

---

<div class="post-metadata">

**Author:** ![Dror1](https://avatars.discourse-cdn.com/v4/letter/d/d07c76/32.png) [@Dror1](https://discourse.slicer.org/u/Dror1)\
**Post date:** [December 27, 2022, 7:32am UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/4 "2022-12-27T07:32:46Z")

</div>

Thank you very much, it’s working.

---

<div class="post-metadata">

**Author:** ![RenskeS](https://avatars.discourse-cdn.com/v4/letter/r/e99b99/32.png) [@RenskeS](https://discourse.slicer.org/u/RenskeS)\
**Post date:** [December 27, 2022, 9:38am UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/5 "2022-12-27T09:38:28Z")

</div>

I got the exact same error message while using the TotalSegmentator module. I did already install git (git version 2.39.0.windows.2), restarted Slicer and my laptop, but still get the same message when pressing “Apply” in the module. What could be other possibilities to fix this error?

Thanks in advance for thinking along!

---

<div class="post-metadata">

**Author:** ![rbumm](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/rbumm/32/9404_2.png) [@rbumm](https://discourse.slicer.org/u/rbumm)\
**Post date:** [December 27, 2022, 12:46pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/6 "2022-12-27T12:46:05Z")

</div>

If you are on Windows, could you try to install TotalSegmentator from the command line:

```auto
"C:\Users\yourname\AppData\Local\NA-MIC\Slicer 5.2.1\bin/PythonSlicer.EXE" -m pip install git+https://github.com/wasserth/TotalSegmentator.git --no-deps

```

and post eventual error messages?

---

<div class="post-metadata">

**Author:** ![RenskeS](https://avatars.discourse-cdn.com/v4/letter/r/e99b99/32.png) [@RenskeS](https://discourse.slicer.org/u/RenskeS)\
**Post date:** [December 27, 2022, 1:00pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/7 "2022-12-27T13:00:41Z")

</div>

I do not get an error message when entering the command line and installing TotalSegmentator, the installation is fully successful. Unfortunately, I still get the same error when applying the module in Slicer.

---

<div class="post-metadata">

**Author:** ![rbumm](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/rbumm/32/9404_2.png) [@rbumm](https://discourse.slicer.org/u/rbumm)\
**Post date:** [December 27, 2022, 1:07pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/8 "2022-12-27T13:07:18Z")

</div>

Are you getting any messages here?

 ![image](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/4/e/4e14ae4fe74657ebf040e76db1602be2f1cd8670.png)

Could you specify your hardware and run 3D Slicer in admin mode for a test?  
Please use the CTChest demo dataset from “Sample Data”

---

<div class="post-metadata">

**Author:** ![RenskeS](https://avatars.discourse-cdn.com/v4/letter/r/e99b99/32.png) [@RenskeS](https://discourse.slicer.org/u/RenskeS)\
**Post date:** [December 27, 2022, 1:27pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/9 "2022-12-27T13:27:49Z")

</div>

![image](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/1/9/19b91f6af189b47a5b955fe20e7ef9d3a0080c42.png)

This is what I get when running in admin mode.

I have Windows 10 Home on a Lenovo Thinkpad T460s with the following processor: Intel(R) Core™ i5-6200U CPU @ 2.30GHz, 2400 Mhz, 2 Core(s), 4 Logical Processor(s)

---

<div class="post-metadata">

**Author:** ![rbumm](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/rbumm/32/9404_2.png) [@rbumm](https://discourse.slicer.org/u/rbumm)\
**Post date:** [December 27, 2022, 1:41pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/10 "2022-12-27T13:41:48Z")

</div>

What happens if you go to the “PyTorch” extension and press the button “Install PyTorch”? Probably the same?

---

<div class="post-metadata">

**Author:** ![RenskeS](https://avatars.discourse-cdn.com/v4/letter/r/e99b99/32.png) [@RenskeS](https://discourse.slicer.org/u/RenskeS)\
**Post date:** [December 27, 2022, 3:51pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/11 "2022-12-27T15:51:53Z")

</div>

Yes that is correct, then I get the same error

---

<div class="post-metadata">

**Author:** ![rbumm](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/rbumm/32/9404_2.png) [@rbumm](https://discourse.slicer.org/u/rbumm)\
**Post date:** [December 27, 2022, 4:06pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/12 "2022-12-27T16:06:07Z")

</div>

@lassoan has just made a helpful update of the PyTorch extension:

![image](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/0/0/00b0bf51a0e1130c1afda4e137ce364713b579d0.png)

you may want to uninstall and reinstall PyTorch after updating. Please bear in mind that your laptop will run TotalSegmentator in CPU mode.

@lassoan it would be great if you could add a “Check CUDA” button

---

<div class="post-metadata">

**Author:** ![RenskeS](https://avatars.discourse-cdn.com/v4/letter/r/e99b99/32.png) [@RenskeS](https://discourse.slicer.org/u/RenskeS)\
**Post date:** [December 27, 2022, 4:46pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/13 "2022-12-27T16:46:48Z")

</div>

Thanks, I indeed read it somewhere else as well. This update fixed the first error I had, @lassoan thank you for that!

With the reinstalled PyTorch I got some errors for missing modules, which I pip installed. My access got denied when installing xvfbwrapper and it mentioned that I got a too new version of ITK-snap as well for totalsegmentator. In Slicer I currently get the following error:

Processing started  
Writing input file to C:/Users/schra/AppData/Local/Temp/Slicer/\_\_SlicerTemp\_\_2022-12-27\_17+37+33.895/total-segmentator-input.nii  
Creating segmentations with TotalSegmentator AI…  
Total Segmentator arguments: [‘-i’, ‘C:/Users/schra/AppData/Local/Temp/Slicer/\_\_SlicerTemp\_\_2022-12-27\_17+37+33.895/total-segmentator-input.nii’, ‘-o’, ‘C:/Users/schra/AppData/Local/Temp/Slicer/\_\_SlicerTemp\_\_2022-12-27\_17+37+33.895/segmentation’, ‘–ml’, ‘–task’, ‘total’, ‘–fast’]

with

Traceback (most recent call last):  
File “C:\Users\schra\AppData\Local\NA-MIC\Slicer 5.2.1\bin\Python\slicer\util.py”, line 2961, in tryWithErrorDisplay  
yield  
File “C:/Users/schra/AppData/Local/NA-MIC/Slicer 5.2.1/NA-MIC/Extensions-31317/TotalSegmentator/lib/Slicer-5.2/qt-scripted-modules/TotalSegmentator.py”, line 258, in onApplyButton  
self.logic.process(self.ui.inputVolumeSelector.currentNode(), self.ui.outputSegmentationSelector.currentNode(),  
File “C:/Users/schra/AppData/Local/NA-MIC/Slicer 5.2.1/NA-MIC/Extensions-31317/TotalSegmentator/lib/Slicer-5.2/qt-scripted-modules/TotalSegmentator.py”, line 714, in process  
proc = slicer.util.launchConsoleProcess(totalSegmentatorCommand + options)  
File “C:\Users\schra\AppData\Local\NA-MIC\Slicer 5.2.1\bin\Python\slicer\util.py”, line 3463, in launchConsoleProcess  
proc = subprocess.Popen(args, env=startupEnv, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, universal\_newlines=True, startupinfo=info, cwd=cwd)  
File “C:\Users\schra\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Lib\subprocess.py”, line 951, in **init**  
self.\_execute\_child(args, executable, preexec\_fn, close\_fds,  
File “C:\Users\schra\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Lib\subprocess.py”, line 1420, in \_execute\_child  
hp, ht, pid, tid = \_winapi.CreateProcess(executable, args,  
OSError: [WinError 193] %1 is not a valid Win32 application

Was installing the separate missing modules not the correct thing to do? And what can I do to overrule the denial of the missing xvfbwrapper module? Or is this not the way to go?

Again, thanks a lot for thinking along!

---

<div class="post-metadata">

**Author:** ![RenskeS](https://avatars.discourse-cdn.com/v4/letter/r/e99b99/32.png) [@RenskeS](https://discourse.slicer.org/u/RenskeS)\
**Post date:** [December 27, 2022, 5:24pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/14 "2022-12-27T17:24:46Z")

</div>

I managed to install the xvfbwrapper and right ITK-snap version. Everything seems to work now!

Thanks for the help!

---

<div class="post-metadata">

**Author:** ![R.Boellaard](https://avatars.discourse-cdn.com/v4/letter/r/71c47a/32.png) [@R.Boellaard](https://discourse.slicer.org/u/R.Boellaard)\
**Post date:** [December 28, 2022, 2:13pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/15 "2022-12-28T14:13:13Z")

</div>

Hi there,

I installed Git etc. I ininstalled PyTorch and got a message that it was installed. I then tried install PyTorch, but nothing happens, even not messages…is there any additional package I need such that pytorch wil be installed?

Thnx  
Ronald

---

<div class="post-metadata">

**Author:** ![rbumm](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/rbumm/32/9404_2.png) [@rbumm](https://discourse.slicer.org/u/rbumm)\
**Post date:** [December 28, 2022, 3:54pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/16 "2022-12-28T15:54:57Z")

</div>

Hi Ronald,

Have you been using the PyTorch extension for uninstalling and then installing PyTorch [as outlined above](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/12)?

---

<div class="post-metadata">

**Author:** ![R.Boellaard](https://avatars.discourse-cdn.com/v4/letter/r/71c47a/32.png) [@R.Boellaard](https://discourse.slicer.org/u/R.Boellaard)\
**Post date:** [December 28, 2022, 4:17pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/17 "2022-12-28T16:17:40Z")

</div>

Dear Rudolf

I tried several times and finally I disconnected my PC and used wifi with eduroam and now it was able to unistall and install pytorch. But I encountered the next error "Processing started

Writing input file to C:/Users/Ronald/AppData/Local/Temp/Slicer/\_\_SlicerTemp\_\_2022-12-28\_17+14+28.271/total-segmentator-input.nii

Creating segmentations with TotalSegmentator AI…

Total Segmentator arguments: [‘-i’, ‘C:/Users/Ronald/AppData/Local/Temp/Slicer/\_\_SlicerTemp\_\_2022-12-28\_17+14+28.271/total-segmentator-input.nii’, ‘-o’, ‘C:/Users/Ronald/AppData/Local/Temp/Slicer/\_\_SlicerTemp\_\_2022-12-28\_17+14+28.271/segmentation’, ‘–ml’, ‘–task’, ‘total’, ‘–fast’]

Traceback (most recent call last):

File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Scripts\TotalSegmentator”, line 10, in

import nibabel as nib

ModuleNotFoundError: No module named ‘nibabel’

"

So, it seems i need to install the nibabel package. Should I do so within slider using the python window or do you recommend to do so thru cmd window.

Thnx  
Ronald

![Outlook-cid_image0.png](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/5/8/5832dc008835c3900a4e9e67a9901d64ac773c27.png)

---

<div class="post-metadata">

**Author:** ![rbumm](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/rbumm/32/9404_2.png) [@rbumm](https://discourse.slicer.org/u/rbumm)\
**Post date:** [December 28, 2022, 4:37pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/18 "2022-12-28T16:37:15Z")

</div>

Please “Upgrade” the Totalsegmentator package first from the extension, now with running public WLAN.

 ![image](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/8/3/835ba999a8c24c9481ec43ea3eaaccae86ec910a.png)

If that does not help, you could pip install missing packages from the Python Interactor like this:

```auto
slicer.util.pip_install("nibabel")

```

---

<div class="post-metadata">

**Author:** ![R.Boellaard](https://avatars.discourse-cdn.com/v4/letter/r/71c47a/32.png) [@R.Boellaard](https://discourse.slicer.org/u/R.Boellaard)\
**Post date:** [December 28, 2022, 4:57pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/19 "2022-12-28T16:57:34Z")

</div>

Some steps further:-)

Still an error:  
Processing started  
Writing input file to C:/Users/Ronald/AppData/Local/Temp/Slicer/\_\_SlicerTemp\_\_2022-12-28\_17+54+58.904/total-segmentator-input.nii  
Creating segmentations with TotalSegmentator AI…  
Total Segmentator arguments: [‘-i’, ‘C:/Users/Ronald/AppData/Local/Temp/Slicer/\_\_SlicerTemp\_\_2022-12-28\_17+54+58.904/total-segmentator-input.nii’, ‘-o’, ‘C:/Users/Ronald/AppData/Local/Temp/Slicer/\_\_SlicerTemp\_\_2022-12-28\_17+54+58.904/segmentation’, ‘–ml’, ‘–task’, ‘total’, ‘–fast’]

Please cite the following paper when using nnUNet:

Isensee, F., Jaeger, P.F., Kohl, S.A.A. et al. “nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation.” Nat Methods (2020). [nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation | Nature Methods](https://doi.org/10.1038/s41592-020-01008-z)

If you have questions or suggestions, feel free to open an issue at [GitHub - MIC-DKFZ/nnUNet](https://github.com/MIC-DKFZ/nnUNet)

preprocessing C:\Users\Ronald\AppData\Local\Temp\nnunet\_tmp\_8pv33ag1\s01.nii.gz  
using preprocessor GenericPreprocessor  
before crop: (1, 293, 200, 200) after crop: (1, 293, 200, 200) spacing: [3. 3. 3.]

no resampling necessary  
no resampling necessary  
before: {‘spacing’: array([3., 3., 3.]), ‘spacing\_transposed’: array([3., 3., 3.]), ‘data.shape (data is transposed)’: (1, 293, 200, 200)}  
after: {‘spacing’: array([3., 3., 3.]), ‘data.shape (data is resampled)’: (1, 293, 200, 200)}

(1, 293, 200, 200)  
This worker has ended successfully, no errors to report  
Traceback (most recent call last):  
File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Scripts\TotalSegmentator”, line 201, in   
main()  
File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Scripts\TotalSegmentator”, line 179, in main  
seg = nnUNet\_predict\_image(args.input, args.output, task\_id, model=model, folds=folds,  
File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Lib\site-packages\totalsegmentator\nnunet.py”, line 232, in nnUNet\_predict\_image  
nnUNet\_predict(tmp\_dir, tmp\_dir, task\_id, model, folds, trainer, tta)  
File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Lib\site-packages\totalsegmentator\nnunet.py”, line 106, in nnUNet\_predict  
predict\_from\_folder(model\_folder\_name, dir\_in, dir\_out, folds, save\_npz, num\_threads\_preprocessing,  
File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Lib\site-packages\nnunet\inference\predict.py”, line 668, in predict\_from\_folder  
return predict\_cases\_fastest(model, list\_of\_lists[part\_id::num\_parts], output\_files[part\_id::num\_parts], folds,  
File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Lib\site-packages\nnunet\inference\predict.py”, line 493, in predict\_cases\_fastest  
res = trainer.predict\_preprocessed\_data\_return\_seg\_and\_softmax(d, do\_mirroring=do\_tta,  
File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Lib\site-packages\nnunet\training\network\_training\nnUNetTrainerV2.py”, line 211, in predict\_preprocessed\_data\_return\_seg\_and\_softmax  
ret = super().predict\_preprocessed\_data\_return\_seg\_and\_softmax(data,  
File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Lib\site-packages\nnunet\training\network\_training\nnUNetTrainer.py”, line 516, in predict\_preprocessed\_data\_return\_seg\_and\_softmax  
ret = self.network.predict\_3D(data, do\_mirroring=do\_mirroring, mirror\_axes=mirror\_axes,  
File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Lib\site-packages\nnunet\network\_architecture\neural\_network.py”, line 147, in predict\_3D  
res = self.\_internal\_predict\_3D\_3Dconv\_tiled(x, step\_size, do\_mirroring, mirror\_axes, patch\_size,  
File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Lib\site-packages\nnunet\network\_architecture\neural\_network.py”, line 384, in \_internal\_predict\_3D\_3Dconv\_tiled  
predicted\_patch = self.\_internal\_maybe\_mirror\_and\_pred\_3D(  
File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Lib\site-packages\nnunet\network\_architecture\neural\_network.py”, line 510, in \_internal\_maybe\_mirror\_and\_pred\_3D  
result\_torch = to\_cuda(result\_torch, gpu\_id=self.get\_device())  
File “C:\Users\Ronald\AppData\Local\NA-MIC\Slicer 5.2.1\lib\Python\Lib\site-packages\nnunet\utilities\to\_torch.py”, line 31, in to\_cuda  
data = data.cuda(gpu\_id, non\_blocking=non\_blocking)  
RuntimeError: CUDA out of memory. Tried to allocate 356.00 MiB (GPU 0; 6.00 GiB total capacity; 4.75 GiB already allocated; 0 bytes free; 4.78 GiB reserved in total by PyTorch) If reserved memory is \>\> allocated memory try setting max\_split\_size\_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH\_CUDA\_ALLOC\_CONF  
Exception ignored in: \<totalsegmentator.libs.DummyFile object at 0x0000020E346E5250\>  
AttributeError: ‘DummyFile’ object has no attribute ‘flush’  
Using ‘fast’ option: resampling to lower resolution (3mm)  
Resampling…  
Resampled in 4.12s  
Predicting…

I got CUDA out of memory. Should I try to install the CPU pytorch version? I do have an nvidia card, but the amount of memory is very low…

Thnx  
Ronald

---

<div class="post-metadata">

**Author:** ![rbumm](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/rbumm/32/9404_2.png) [@rbumm](https://discourse.slicer.org/u/rbumm)\
**Post date:** [December 28, 2022, 6:24pm UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/20 "2022-12-28T18:24:59Z")

</div>

No personal experience, but yes, you may want to try that, uninstall PyTorch with the extension and reinstall it in CPU mode:

![image](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/3/4/34c5f816f3a704394d0b3519fe6971ceee2f0f17.png)

Please let us know how it works.

---

<div class="post-metadata">

**Author:** ![R.Boellaard](https://avatars.discourse-cdn.com/v4/letter/r/71c47a/32.png) [@R.Boellaard](https://discourse.slicer.org/u/R.Boellaard)\
**Post date:** [December 29, 2022, 7:26am UTC](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925/21 "2022-12-29T07:26:14Z")

</div>

Dear Rudolf

It works! Many thanks for your help and suggestions. It is relatively fast (even with CPU) and worked quite well even for a low dose CT (done along with a PET scan)…so it generates quite well segmentations for a poor quality scan.

Regards  
Ronald

[Next page](https://discourse.slicer.org/t/error-while-using-total-segmentator/26925.md?page=2)