search

NVIDIA / DeepLearningExamples

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
13.56k stars 3.23k forks source link

[brats22/nnunet/pytorch] inference problem on the validation dataset #1291

Open abbas695 opened 1 year ago

abbas695 commented 1 year ago

Related to brats22/nnunet/pytorch

the bug orig_lbl = load_data(self.data_path, "*_orig_lbl.npy")

the line above which is line 51 in nnUNet/data_loading/data_module.py is producing an assertion error due to the assertion in the load_data function as it expects orig_lbl.npy extension and this is not possible in the validation dataset as there is no labels To Reproduce Steps to reproduce the behavior: follow the brats22 notebook until the inference part on the validation dataset Expected behavior what i expected to happen was that the predict mode would not assert the existence of data related to the labels Environment google colab free edition environment

michal2409 commented 1 year ago

Hi @abbas695, thank you for reporting that. I will prepare a fixed version, but it might take a few days until it is public. In the meantime, you can remove assert statement from here, which should resolve the issue.

abbas695 commented 1 year ago

thank you @michal2409 , have a great day.