Ошибка при обучении nnunet Нет такого файла или каталога: nnunet/nnUNet_preprocessed/Dataset100_FMS/nnUNetPlans_3d_fullr ⇐ Python

[Anonymous]

Я уже тренировал 3 сгиба, используя один и тот же код, теперь получаю эту ошибку. Файл json в nnUNet_preprocessed, созданный во время предварительной обработки, на самом деле называется nnUNetResEncUNetMPlans, а не nnUNetPlans_3d_fullres, как в ошибке.
subprocess.call("nnUNetv2_train " + opts.dataset_name_or_id + " " + opts.configuration + " " + str(opts.fold) + ' -p ' + opts.training_plans_identifier + " --npz", shell=True)
parser = argparse.ArgumentParser()
parser.add_argument('--func', help='Function to call', type=str, default='train_nnUNet')
parser.add_argument('--dataset_name_or_id', help='nnUnet dataset_name_or_id', type=str, default='100')
#parser.add_argument('--configuration', help='nnUnet configuration', type=str, default='2d')
parser.add_argument('--configuration', help='nnUnet configuration', type=str, default='3d_fullres')
parser.add_argument('--fold', help='nnUnet fold number from 5-fold cross validation', type=str, default=3)
parser.add_argument('--nnUNetTrainer', help='nnUnet nnUNetTrainer', type=str, default='nnUNetTrainer_5epochs')
parser.add_argument('--plans_identifier', help='nnUnet plans_identifier', type=str, default="nnUNetPlannerResEncM")

parser.add_argument('--training_plans_identifier', help='nnUnet plans_identifier_for_training', type=str, default="nnUNetResEncUNetMPlans")

Ошибка следующая
/media/foellmer/SSD/FMS/code/nnUNet/nnUNet-master/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py:164: FutureWarning: torch.cuda.amp.GradScaler(args...) is deprecated. Please use torch.amp.GradScaler('cuda', args...) instead.
self.grad_scaler = GradScaler() if self.device.type == 'cuda' else None
Using device: cuda:0

#######################################################################
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.
#######################################################################

2025-01-11 16:34:35.023186: do_dummy_2d_data_aug: False
Traceback (most recent call last):

File "/home/foellmer/anaconda3/envs/env_nnUNet8/bin/nnUNetv2_train", line 8, in
sys.exit(run_training_entry())

File "/media/foellmer/SSD/FMS/code/nnUNet/nnUNet-master/nnunetv2/run/run_training.py", line 275, in run_training_entry
run_training(args.dataset_name_or_id, args.configuration, args.fold, args.tr, args.p, args.pretrained_weights,

File "/media/foellmer/SSD/FMS/code/nnUNet/nnUNet-master/nnunetv2/run/run_training.py", line 211, in run_training
nnunet_trainer.run_training()

File "/media/foellmer/SSD/FMS/code/nnUNet/nnUNet-master/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py", line 1362, in run_training
self.on_train_start()

File "/media/foellmer/SSD/FMS/code/nnUNet/nnUNet-master/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py", line 903, in on_train_start
self.dataloader_train, self.dataloader_val = self.get_dataloaders()

File "/media/foellmer/SSD/FMS/code/nnUNet/nnUNet-master/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py", line 652, in get_dataloaders
dataset_tr, dataset_val = self.get_tr_and_val_datasets()

File "/media/foellmer/SSD/FMS/code/nnUNet/nnUNet-master/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py", line 608, in get_tr_and_val_datasets
tr_keys, val_keys = self.do_split()

File "/media/foellmer/SSD/FMS/code/nnUNet/nnUNet-master/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py", line 567, in do_split
dataset = nnUNetDataset(self.preprocessed_dataset_folder, case_identifiers=None,

File "/media/foellmer/SSD/FMS/code/nnUNet/nnUNet-master/nnunetv2/training/dataloading/nnunet_dataset.py", line 40, in __init__
case_identifiers = get_case_identifiers(folder)

File "/media/foellmer/SSD/FMS/code/nnUNet/nnUNet-master/nnunetv2/training/dataloading/utils.py", line 77, in get_case_identifiers
case_identifiers = [i[:-4] for i in os.listdir(folder) if i.endswith("npz") and (i.find("segFromPrevStage") == -1)]

FileNotFoundError: [Errno 2] No such file or directory: '/media/foellmer/SSD/FMS/data/nnunet/nnUNet_preprocessed/Dataset100_FMS/nnUNetPlans_3d_fullres'
Out[4]: 1


Подробнее здесь: https://stackoverflow.com/questions/793 ... eprocessed