Problem in prediction: AssertionError: Spacing length should be 3 for 3D images

[luuciaborrego02]

I have preprocessed the images from the Decathlon prostate database (I previously converted them) and when I train, I get the message “training done” and when I make the prediction I get this:

2024-11-09 12:10:05.694911: Training done.
2024-11-09 12:10:06.177104: Using splits from existing split file: C:\Users\lucia\Desktop\nnUNet_preprocessed\Dataset002_prostate\splits_final.json
2024-11-09 12:10:06.177104: The split file contains 5 splits.
2024-11-09 12:10:06.177104: Desired fold for training: 0
2024-11-09 12:10:06.185123: This split has 25 training and 7 validation cases.
2024-11-09 12:10:06.185123: predicting prostate_00
2024-11-09 12:10:09.071009: predicting prostate_04
2024-11-09 12:10:10.271552: predicting prostate_14
2024-11-09 12:10:11.485538: predicting prostate_20
2024-11-09 12:10:12.708740: predicting prostate_25
2024-11-09 12:10:13.947531: predicting prostate_31
label_handling False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\utilities\label_handling
default_resampling False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\preprocessing\resampling
2024-11-09 12:10:15.173128: predicting prostate_42
label_handling False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\utilities\label_handling
default_resampling False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\preprocessing\resampling
base_reader_writer False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\imageio
natural_image_reader_writer False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\imageio
nibabel_reader_writer False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\imageio
reader_writer_registry False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\imageio
Spacing: (0.6000000238418579, 0.6000003218650818, 4.000002384185791, 1.0), Length: 4
label_handling False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\utilities\label_handling
default_resampling False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\preprocessing\resampling
base_reader_writer False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\imageio
natural_image_reader_writer False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\imageio
nibabel_reader_writer False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\imageio
reader_writer_registry False
C:\Users\lucia\Desktop\nnUNet\nnunetv2\imageio
Spacing: (0.6000000238418579, 0.6000001430511475, 4.000000476837158, 1.0), Length: 4
multiprocessing.pool.RemoteTraceback:
"""
Traceback (most recent call last):
File "C:\Users\lucia\AppData\Local\Programs\Python\Python310\lib\multiprocessing\pool.py", line 125, in worker
result = (True, func(*args, **kwds))
File "C:\Users\lucia\AppData\Local\Programs\Python\Python310\lib\multiprocessing\pool.py", line 51, in starmapstar
return list(itertools.starmap(args[0], args[1]))
File "C:\Users\lucia\Desktop\nnUNet\nnunetv2\inference\export_prediction.py", line 105, in export_prediction_from_logits
rw.write_seg(segmentation_final, output_file_truncated + dataset_json_dict_or_file['file_ending'],
File "C:\Users\lucia\Desktop\nnUNet\nnunetv2\imageio\simpleitk_reader_writer.py", line 124, in write_seg
assert len(spacing) == 3, "Spacing length should be 3 for 3D images"
AssertionError: Spacing length should be 3 for 3D images
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\Users\lucia\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\lucia\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "C:\Users\lucia\nnunet_env\Scripts\nnUNetv2_train.exe_main.py", line 7, in
sys.exit(run_training_entry())
File "C:\Users\lucia\Desktop\nnUNet\nnunetv2\run\run_training.py", line 268, in run_training_entry
run_training(args.dataset_name_or_id, args.configuration, args.fold, args.tr, args.p, args.pretrained_weights,
File "C:\Users\lucia\Desktop\nnUNet\nnunetv2\run\run_training.py", line 208, in run_training
nnunet_trainer.perform_actual_validation(export_validation_probabilities)
File "C:\Users\lucia\Desktop\nnUNet\nnunetv2\training\nnUNetTrainer\nnUNetTrainer.py", line 1248, in perform_actual_validation
_ = [r.get() for r in results]
File "C:\Users\lucia\Desktop\nnUNet\nnunetv2\training\nnUNetTrainer\nnUNetTrainer.py", line 1248, in
_ = [r.get() for r in results]
File "C:\Users\lucia\AppData\Local\Programs\Python\Python310\lib\multiprocessing\pool.py", line 774, in get
raise self._value
AssertionError: Spacing length should be 3 for 3D images

[seziegler]

Hi @luuciaborrego02 ,
the spacing of prostate_31 seems to have an additional value of 1.0. Can you check that file manually and adjust the spacing?