Giters

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.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[Question]AttributeError: 'NoneType' object has no attribute 'glob'

sunqiangzai opened this issue · comments

commented

❓ Question

the error occurs when I run the following command:
nndet_consolidate 000 RetinaUNetV001_D3V001_3d --sweep_boxes

 INFO looking for models in /opt/models/Task000D3_Example/RetinaUNetV001_D3V001_3d
INFO Found training dirs: [PosixPath('/opt/models/Task000D3_Example/RetinaUNetV001_D3V001_3d/fold0'), None, None, None, None]
INFO Consolidate models
Traceback (most recent call last):
  File "/opt/conda/bin/nndet_consolidate", line 33, in <module>
    sys.exit(load_entry_point('nndet', 'console_scripts', 'nndet_consolidate')())
  File "/opt/code/nndet/nndet/utils/check.py", line 62, in wrapper
    return func(*args, **kwargs)
  File "/opt/code/nndet/scripts/consolidate.py", line 159, in main
    consolidate_models(training_dirs, target_dir, ckpt)
  File "/opt/code/nndet/scripts/consolidate.py", line 46, in consolidate_models
    model_paths = list(sd.glob('*.ckpt'))
AttributeError: 'NoneType' object has no attribute 'glob'

�

commented

consolidate is only needed when combining the models from different folds, it seems like you only trained fold 0 from the output and thus nnDetectionc an not find the other ones.

commented

This issue is stale because it has been open for 30 days with no activity.

commented

This issue was closed because it has been inactive for 14 days since being marked as stale.