ValueError: zero-size array to reduction operation minimum which has no identity.

[AIfanss]

hi, when I run the nnUNet_plan_and_preprocess.py, ValueError: zero-size array to reduction operation minimum which has no identity appeared, it happened when I run it on my own dataset while on the given official dataset everything was fine. So there has to be something wrong with my own dataset, but I can tell the difference, could someone help me with this ?

[FabianIsensee]

Have you tried nnUNet_plan_and_preprocess [...] --verify_dataset_integrity?

[billhhh]

Tried, returns the same issue

[OceaneerDs]

Hi there!
@AIfanss I probably ran into the same error with nnUNetv2_plan_and_preprocess -d 40 --verify_dataset_integrity . Did you solve yours?
My error source seems to be:
UNet\nnUNet\nnunetv2\experiment_planning\dataset_fingerprint\fingerprint_extractor.py
--> min': float(np.min(foreground_intensities_per_channel[i]))

foreground_intensities_per_channel[i] is of size zero.

Output of nnUNetv2_plan_and_preprocess -d 40 --verify_dataset_integrity :

_Fingerprint extraction...
Dataset040_Voids
Using <class 'nnunetv2.imageio.natural_image_reager_writer.NaturalImage2DIO'> as reader/writer

####################
verify_dataset_integrity Done.
If you didn't see any error messages then your dataset is most likely OK!
####################

Using <class 'nnunetv2.imageio.natural_image_reager_writer.NaturalImage2DIO'> as reader/writer_
...\Desktop\Projects\UNet\unet_venv\lib\site-packages\numpy\core\fromnumeric.py:3504: RuntimeWarning: Mean of empty slice.
return _methods._mean(a, axis=axis, dtype=dtype,
...\Desktop\Projects\UNet\unet_venv\lib\site-packages\numpy\core_methods.py:129: RuntimeWarning: invalid value encountered in scalar divide
ret = ret.dtype.type(ret / rcount)
...\Desktop\Projects\UNet\unet_venv\lib\site-packages\numpy\core_methods.py:206: RuntimeWarning: Degrees of freedom <= 0 for slice
ret = _var(a, axis=axis, dtype=dtype, out=out, ddof=ddof,
...\Desktop\Projects\UNet\unet_venv\lib\site-packages\numpy\core_methods.py:163: RuntimeWarning: invalid value encountered in divide
arrmean = um.true_divide(arrmean, div, out=arrmean,
...\Desktop\Projects\UNet\unet_venv\lib\site-packages\numpy\core_methods.py:198: RuntimeWarning: invalid value encountered in scalar divide
ret = ret.dtype.type(ret / rcount)
Traceback (most recent call last):
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File ..\Desktop\Projects\UNet\unet_venv\Scripts\nnUNetv2_plan_and_preprocess.exe_main.py", line 7, in
File ...\Desktop\Projects\UNet\nnUNet\nnunetv2\experiment_planning\plan_and_preprocess_entrypoints.py", line 182, in plan_and_preprocess_entry
extract_fingerprints(args.d, args.fpe, args.npfp, args.verify_dataset_integrity, args.clean, args.verbose)
File ...\Desktop\Projects\UNet\nnUNet\nnunetv2\experiment_planning\plan_and_preprocess_api.py", line 47, in extract_fingerprints
extract_fingerprint_dataset(d, fingerprint_extractor_class, num_processes, check_dataset_integrity, clean,
File ...\Desktop\Projects\UNet\nnUNet\nnunetv2\experiment_planning\plan_and_preprocess_api.py", line 33, in extract_fingerprint_dataset
return fpe.run(overwrite_existing=clean)
File ...\Desktop\Projects\UNet\nnUNet\nnunetv2\experiment_planning\dataset_fingerprint\fingerprint_extractor.py", line 185, in run
'min': float(np.min(foreground_intensities_per_channel[i])),
File ...\Desktop\Projects\UNet\unet_venv\lib\site-packages\numpy\core\fromnumeric.py", line 2953, in min
return _wrapreduction(a, np.minimum, 'min', axis, None, out,
File ...\Desktop\Projects\UNet\unet_venv\lib\site-packages\numpy\core\fromnumeric.py", line 88, in _wrapreduction
return ufunc.reduce(obj, axis, dtype, out, passkwargs)
ValueError: zero-size array to reduction operation minimum which has no identity

[adriroyu]

Hi! I ran into the same error. Did you managed to solve it?

[OceaneerDs]

Hi @adriroyu!
No, I stopped trying after a short time and implemented my own solution.

[billhhh]

Same issue here

[billhhh]

Solved, thanks, for me I wrongly called copy_BraTS_segmentation_and_convert_labels_to_nnUNet() function, as I modify my script based on brats one. Direct copy of masks solved this issue