fold =5

[sghassemi315]

I ran nnUNetv2_train Dataset888_bbmri 2d 5 --npz and now I have file named fold 5,as it shoud be[0,1,2,3,4] the result I have now is it wrong?and it is in epoch 900 and continuing yet!!!

[dojoh]

The number given specifies the fold that is run and should be in [0,1,2,3,4] or 'all'. nnUnetv2 automatically performs 5 fold cross-validation. If the number is bigger than 4 a random 80:20 split is created and evaluated.

[sghassemi315]

I trained all fold 3d full res now how to run it on my test data like imagesTs for prediction, I could not find any command like for training. Thank you

…

On Wed, 2 Aug 2023 at 12:03, dojoh ***@***.***> wrote: The number given specifies the fold that is run and should be in [0,1,2,3,4] or 'all'. nnUnetv2 automatically performs 5 fold cross-validation. If the number is bigger than 4 a random 80:20 split is created and evaluated. — Reply to this email directly, view it on GitHub <#1544 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BBC4ZZ4CAPE4BUDXCRRJPZ3XTIQWXANCNFSM6AAAAAA2AO7K54> . You are receiving this because you authored the thread.Message ID: ***@***.***>

[dojoh]

You can find information about bow to run inference in the documentation:
https://github.com/MIC-DKFZ/nnUNet/blob/master/documentation/how_to_use_nnunet.md#run-inference

[sghassemi315]

Hello I hope you are well. I get this error when I want to do predict for my test dataset. (nn_UNet) :/shared/sghasemi/dataset/nnUNet_raw$ nnUNetv2_predict -d Dataset999_blackbonemri -i INPUT_FOLDER -o OUTPUT_FOLDER -f 0 1 2 3 4 -tr nnUNetTrainer -c 3d_fullres -p nnUNetPlans ####################################################################### Please cite the following paper when using nnU-Net: Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2), 203-211. ####################################################################### There are 26 cases in the source folder I am process 0 out of 1 (max process ID is 0, we start counting with 0!) There are 26 cases that I would like to predict Error: mkl-service + Intel(R) MKL: MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1 library. Try to import numpy first or set the threading layer accordingly. Set MKL_SERVICE_FORCE_INTEL to force it. Error: mkl-service + Intel(R) MKL: MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1 library. Try to import numpy first or set the threading layer accordingly. Set MKL_SERVICE_FORCE_INTEL to force it. Error: mkl-service + Intel(R) MKL: MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1 library. Try to import numpy first or set the threading layer accordingly. Set MKL_SERVICE_FORCE_INTEL to force it. Traceback (most recent call last): File "/home/sghassemi/anaconda3/envs/nn_UNet/bin/nnUNetv2_predict", line 33, in <module> sys.exit(load_entry_point('nnunetv2', 'console_scripts', 'nnUNetv2_predict')()) File "/home/sghassemi/Desktop/nnUNet/nnunetv2/inference/predict_from_raw_data.py", line 838, in predict_entry_point predictor.predict_from_files(args.i, args.o, save_probabilities=args.save_probabilities, File "/home/sghassemi/Desktop/nnUNet/nnunetv2/inference/predict_from_raw_data.py", line 249, in predict_from_files return self.predict_from_data_iterator(data_iterator, save_probabilities, num_processes_segmentation_export) File "/home/sghassemi/Desktop/nnUNet/nnunetv2/inference/predict_from_raw_data.py", line 342, in predict_from_data_iterator for preprocessed in data_iterator: File "/home/sghassemi/Desktop/nnUNet/nnunetv2/inference/data_iterators.py", line 109, in preprocessing_iterator_fromfiles raise RuntimeError('Background workers died. Look for the error message further up! If there is ' RuntimeError: Background workers died. Look for the error message further up! If there is none then your RAM was full and the worker was killed by the OS. Use fewer workers or get more RAM in that case!

…

On Thu, 3 Aug 2023 at 11:18, dojoh ***@***.***> wrote: You can find information about bow to run inference in the documentation: https://github.com/MIC-DKFZ/nnUNet/blob/master/documentation/how_to_use_nnunet.md#run-inference — Reply to this email directly, view it on GitHub <#1544 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BBC4ZZ6DC43HL4GYUI5PP2LXTNUGNANCNFSM6AAAAAA2AO7K54> . You are receiving this because you authored the thread.Message ID: ***@***.***>

[dojoh]

does following this suggestion help: pytorch/pytorch#37377 (comment)?