-
Notifications
You must be signed in to change notification settings - Fork 298
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Is this downloading in fast mode itended ? it happens every time. #196
Comments
For me it does only download weights once. On consecutive calls it does not happen. |
This is the full output running TotalSegmentator from 3D Slicer without FAST mode.
|
I guess in Slicer it does not recognize the downloaded weights. How do you specify in Slicer where the weights are stored? Do you set |
TOTALSEG_WEIGHTS_PATH was not set, but I also tried setting that environment variable (pointing it to the Slicer script directory). What is the name of the weight file file that should be generated? |
For v2.0.3: The default TOTALSEG_WEIGHTS_PATH is |
I found the downloaded file in the .totalsegmentator directory of my user
dir, it is unzipped, but it gets redownloaded upon every application
ot Totalsegmentator by 3D Slicer. The folder is not protected. .
[image: image.png]
Am Do., 19. Okt. 2023 um 13:15 Uhr schrieb Jakob Wasserthal <
***@***.***>:
… For v2.0.3: The default TOTALSEG_WEIGHTS_PATH is
~/.totalsegmentator/nnunet/results and for the fast model it should
download the file Dataset297_TotalSegmentator_total_3mm_1559subj.zip into
this directory and extract it.
In v2.0.4 the filename has changed slightly to
Dataset297_TotalSegmentator_total_3mm_1559subj_v204.zip.
—
Reply to this email directly, view it on GitHub
<#196 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AEKMXPVFOMETJW3C7SVBNH3YAEDTRAVCNFSM6AAAAAA6ATWYPSVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTONZQGY2TGMBWGY>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
It is a folder, not a file, with several subfolders.
Am Do., 19. Okt. 2023 um 15:30 Uhr schrieb Rudolf B <
***@***.***>:
… I found the downloaded file in the .totalsegmentator directory of my user
dir, it is unzipped, but it gets redownloaded upon every application
ot Totalsegmentator by 3D Slicer. The folder is not protected. .
[image: image.png]
Am Do., 19. Okt. 2023 um 13:15 Uhr schrieb Jakob Wasserthal <
***@***.***>:
> For v2.0.3: The default TOTALSEG_WEIGHTS_PATH is
> ~/.totalsegmentator/nnunet/results and for the fast model it should
> download the file Dataset297_TotalSegmentator_total_3mm_1559subj.zip
> into this directory and extract it.
> In v2.0.4 the filename has changed slightly to
> Dataset297_TotalSegmentator_total_3mm_1559subj_v204.zip.
>
> —
> Reply to this email directly, view it on GitHub
> <#196 (comment)>,
> or unsubscribe
> <https://github.com/notifications/unsubscribe-auth/AEKMXPVFOMETJW3C7SVBNH3YAEDTRAVCNFSM6AAAAAA6ATWYPSVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTONZQGY2TGMBWGY>
> .
> You are receiving this because you authored the thread.Message ID:
> ***@***.***>
>
|
Correct, it should be a folder with subfolders. |
@rbumm I see these progress bars, but I'm not sure if they refer to downloading or just feedback for some processing:
|
Could you shed some light on that Jakob?Sent from my iPhoneOn 19 Oct 2023, at 15:50, Andras Lasso ***@***.***> wrote:
@rbumm I see these progress bars, but I'm not sure if they refer to downloading or just feedback for some processing:
Processing started
Writing input file to C:/Users/andra/AppData/Local/Temp/Slicer/__SlicerTemp__2023-10-19_09+45+37.921/total-segmentator-input.nii
Creating segmentations with TotalSegmentator AI...
Total Segmentator arguments: ['-i', 'C:/Users/andra/AppData/Local/Temp/Slicer/__SlicerTemp__2023-10-19_09+45+37.921/total-segmentator-input.nii', '-o', 'C:/Users/andra/AppData/Local/Temp/Slicer/__SlicerTemp__2023-10-19_09+45+37.921/segmentation', '--ml', '--task', 'total']
0%| | 0/36 [00:00<?, ?it/s]
3%|2 | 1/36 [00:02<01:18, 2.25s/it]
44%|####4 | 16/36 [00:02<00:02, 9.03it/s]
61%|######1 | 22/36 [00:02<00:01, 9.95it/s]
72%|#######2 | 26/36 [00:03<00:00, 10.30it/s]
81%|######## | 29/36 [00:03<00:00, 10.61it/s]
89%|########8 | 32/36 [00:03<00:00, 10.87it/s]
94%|#########4| 34/36 [00:03<00:00, 10.99it/s]
100%|##########| 36/36 [00:04<00:00, 11.13it/s]
100%|##########| 36/36 [00:04<00:00, 8.78it/s]
0%| | 0/36 [00:00<?, ?it/s]
33%|###3 | 12/36 [00:00<00:00, 117.65it/s]
67%|######6 | 24/36 [00:00<00:00, 23.25it/s]
83%|########3 | 30/36 [00:01<00:00, 17.87it/s]
94%|#########4| 34/36 [00:01<00:00, 16.17it/s]
100%|##########| 36/36 [00:01<00:00, 18.62it/s]
0%| | 0/36 [00:00<?, ?it/s]
39%|###8 | 14/36 [00:00<00:00, 138.61it/s]
78%|#######7 | 28/36 [00:01<00:00, 20.15it/s]
97%|#########7| 35/36 [00:01<00:00, 16.23it/s]
100%|##########| 36/36 [00:01<00:00, 18.72it/s]
0%| | 0/36 [00:00<?, ?it/s]
39%|###8 | 14/36 [00:00<00:00, 66.99it/s]
58%|#####8 | 21/36 [00:00<00:00, 22.58it/s]
69%|######9 | 25/36 [00:01<00:00, 18.48it/s]
78%|#######7 | 28/36 [00:01<00:00, 16.51it/s]
83%|########3 | 30/36 [00:01<00:00, 15.72it/s]
89%|########8 | 32/36 [00:01<00:00, 14.99it/s]
94%|#########4| 34/36 [00:01<00:00, 14.14it/s]
100%|##########| 36/36 [00:02<00:00, 13.78it/s]
100%|##########| 36/36 [00:02<00:00, 17.69it/s]
0%| | 0/36 [00:00<?, ?it/s]
39%|###8 | 14/36 [00:00<00:00, 100.00it/s]
67%|######6 | 24/36 [00:01<00:00, 20.29it/s]
81%|######## | 29/36 [00:01<00:00, 17.10it/s]
92%|#########1| 33/36 [00:01<00:00, 15.66it/s]
100%|##########| 36/36 [00:02<00:00, 14.97it/s]
100%|##########| 36/36 [00:02<00:00, 18.00it/s]
If you use this tool please cite: https://pubs.rsna.org/doi/10.1148/ryai.230024
Resampling...
Resampled in 10.76s
Predicting part 1 of 5 ...
Predicting part 2 of 5 ...
Predicting part 3 of 5 ...
Predicting part 4 of 5 ...
Predicting part 5 of 5 ...
Predicted in 104.88s
Resampling...
Saving segmentations...
Saved in 3.18s
Importing segmentation results...
Cleaning up temporary folder...
Processing completed in 147.69 seconds
Processing finished.
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you were mentioned.Message ID: ***@***.***>
|
I've found the root cause of the issue and submitted a pull request with the fix (#202) |
The text was updated successfully, but these errors were encountered: