You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm trying to train nnU-Net with a custom 2D dataset and I get stuck when preprocessing. The dataset contains 165 2D .tif images, so I firstly adapted it to nnU-Net file format following: Task120_Massachusetts_RoadSegm.py. It creates succesfully the folder that contains the data. I called it Task130_Lucchi. The problem comes when running nnUNet_plan_and_preprocess command as follows:
$ nnUNet_plan_and_preprocess -t 130 --verify_dataset_integrity
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). https://doi.org/10.1038/s41592-020-01008-z
If you have questions or suggestions, feel free to open an issue at https://github.com/MIC-DKFZ/nnUNet
Verifying training set
checking case training-0001
Traceback (most recent call last):
File "/home/dfranco/anaconda3/envs/nnunet/bin/nnUNet_plan_and_preprocess", line 33, in <module>
sys.exit(load_entry_point('nnunet', 'console_scripts', 'nnUNet_plan_and_preprocess')())
File "/data2/dfranco/nnUNet/nnunet/experiment_planning/nnUNet_plan_and_preprocess.py", line 77, in main
verify_dataset_integrity(join(nnUNet_raw_data, task_name))
File "/data2/dfranco/nnUNet/nnunet/preprocessing/sanity_checks.py", line 131, in verify_dataset_integrity
assert all([isfile(i) for i in
AssertionError: some image files are missing for case training-0001. Expected files:
['/data2/dfranco/datasets/nnunet/nnUNet_raw_data_base/nnUNet_raw_data/Task130_Lucchi/imagesTr/training-0001_0000.nii.gz', '/data2/dfranco/datasets/nnunet/nnUNet_raw_data_base/nnUNet_raw_data/Task130_Lucchi/imagesTr/training-0001_0001.nii.gz', '/data2/dfranco/datasets/nnunet/nnUNet_raw_data_base/nnUNet_raw_data/Task130_Lucchi/imagesTr/training-0001_0002.nii.gz']
It seems that something is wrong with the filenames as the command expects some files that are not present. Maybe it can be solved easily but I do not know where I failed.
Hello,
I'm trying to train nnU-Net with a custom 2D dataset and I get stuck when preprocessing. The dataset contains 165 2D .tif images, so I firstly adapted it to nnU-Net file format following: Task120_Massachusetts_RoadSegm.py. It creates succesfully the folder that contains the data. I called it
Task130_Lucchi
. The problem comes when runningnnUNet_plan_and_preprocess
command as follows:It seems that something is wrong with the filenames as the command expects some files that are not present. Maybe it can be solved easily but I do not know where I failed.
Thanks a lot for your time!
Extra information:
2D dataset original files
Train
Test
Generated train nii.gz
Generated test nii.gz
The text was updated successfully, but these errors were encountered: