MIC-DKFZ / nnDetection

nnDetection is a self-configuring framework for 3D (volumetric) medical object detection which can be applied to new data sets without manual intervention. It includes guides for 12 data sets that were used to develop and evaluate the performance of the proposed method.
Apache License 2.0
553 stars 98 forks source link

[Bug]Issues occurred while exporting segmentation results during inference #235

Open A-Buzzkill opened 8 months ago

A-Buzzkill commented 8 months ago

:skull: ### Bug

An error occured in line 125, nndet/inference/restore.py when I follow the instruction to export the segmentation results by using this command:

nndet_predict TaskID Modelname -o inference_kwargs.do_seg=True

image the error messag says: image the reason lies in that type(_slices) is list, by converting _slices to tuple, this problem will be solved image

mibaumgartner commented 8 months ago

Thanks for your report, we will fix this with the next release of nnDetection :) Please note that exporting the segmentation is an experimental feature and we can not guarantee perfect functionality.

Best, Michael