SYMBOL INDEX (971 symbols across 169 files) FILE: Finetune/AbdomenAtlas/Atlas_test.py function main (line 78) | def main(): FILE: Finetune/AbdomenAtlas/check.py function read (line 10) | def read(img, transpose=False): function vis (line 23) | def vis(): function check_original (line 71) | def check_original(): function exe (line 130) | def exe(path): function trans_lab (line 158) | def trans_lab(path): function check_pred_vis (line 176) | def check_pred_vis(): function check_pred_acc (line 211) | def check_pred_acc(): FILE: Finetune/AbdomenAtlas/dataset/dataloader_bdmap.py class Sampler (line 67) | class Sampler(torch.utils.data.Sampler): method __init__ (line 68) | def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True... method __iter__ (line 88) | def __iter__(self): method __len__ (line 107) | def __len__(self): method set_epoch (line 110) | def set_epoch(self, epoch): class LoadSelectedImaged (line 114) | class LoadSelectedImaged(MapTransform): method __init__ (line 131) | def __init__( method register (line 156) | def register(self, reader: ImageReader): method __call__ (line 159) | def __call__(self, data, reader: Optional[ImageReader] = None): function get_loader_Atlas (line 179) | def get_loader_Atlas(args): class Filter_Atlas_Labels (line 240) | class Filter_Atlas_Labels(MapTransform): method __call__ (line 244) | def __call__(self, data): FILE: Finetune/AbdomenAtlas/dataset/dataloader_test.py class Sampler (line 67) | class Sampler(torch.utils.data.Sampler): method __init__ (line 68) | def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True... method __iter__ (line 88) | def __iter__(self): method __len__ (line 107) | def __len__(self): method set_epoch (line 110) | def set_epoch(self, epoch): class LoadSelectedImaged (line 114) | class LoadSelectedImaged(MapTransform): method __init__ (line 131) | def __init__( method register (line 156) | def register(self, reader: ImageReader): method __call__ (line 159) | def __call__(self, data, reader: Optional[ImageReader] = None): function get_test_loader_Atlas (line 179) | def get_test_loader_Atlas(args): FILE: Finetune/AbdomenAtlas/main.py function main (line 123) | def main(): function main_worker (line 135) | def main_worker(gpu, args): function init_log (line 295) | def init_log(name, level=logging.INFO): FILE: Finetune/AbdomenAtlas/optimizers/lr_scheduler.py class _LRSchedulerMONAI (line 23) | class _LRSchedulerMONAI(_LRScheduler): method __init__ (line 27) | def __init__(self, optimizer: Optimizer, end_lr: float, num_iter: int,... class LinearLR (line 42) | class LinearLR(_LRSchedulerMONAI): method get_lr (line 47) | def get_lr(self): class ExponentialLR (line 52) | class ExponentialLR(_LRSchedulerMONAI): method get_lr (line 57) | def get_lr(self): class WarmupCosineSchedule (line 62) | class WarmupCosineSchedule(LambdaLR): method __init__ (line 67) | def __init__( method lr_lambda (line 85) | def lr_lambda(self, step): class LinearWarmupCosineAnnealingLR (line 92) | class LinearWarmupCosineAnnealingLR(_LRScheduler): method __init__ (line 93) | def __init__( method get_lr (line 118) | def get_lr(self) -> List[float]: method _get_closed_form_lr (line 156) | def _get_closed_form_lr(self) -> List[float]: FILE: Finetune/AbdomenAtlas/preprocess/try_load.py function main (line 87) | def main(): FILE: Finetune/AbdomenAtlas/trainer.py function train_epoch (line 28) | def train_epoch(model, loader, optimizer, scheduler, scaler, epoch, loss... function val_epoch (line 76) | def val_epoch(model, loader, epoch, acc_func, args, model_inferer=None, ... function save_checkpoint (line 123) | def save_checkpoint(model, epoch, args, filename="model.pt", best_acc=0,... function run_training (line 135) | def run_training( FILE: Finetune/AbdomenAtlas/utils/data_trans.py class Sampler (line 13) | class Sampler(torch.utils.data.Sampler): method __init__ (line 14) | def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True... method __iter__ (line 34) | def __iter__(self): method __len__ (line 53) | def __len__(self): method set_epoch (line 56) | def set_epoch(self, epoch): function get_trans (line 60) | def get_trans(args): class Delete_keys (line 104) | class Delete_keys(MapTransform): method __call__ (line 108) | def __call__(self, data): FILE: Finetune/AbdomenAtlas/utils/mixup.py function mixup (line 5) | def mixup(inputs): FILE: Finetune/AbdomenAtlas/utils/utils.py function resample_3d (line 19) | def resample_3d(img, target_size): function dice (line 27) | def dice(x, y): class AverageMeter (line 36) | class AverageMeter(object): method __init__ (line 37) | def __init__(self): method reset (line 40) | def reset(self): method update (line 46) | def update(self, val, n=1): function distributed_all_gather (line 53) | def distributed_all_gather( function color_map (line 83) | def color_map(dataset='pascal'): function check_dir (line 128) | def check_dir(dir): function read (line 133) | def read(img): FILE: Finetune/Amos/check_test.py function norm (line 30) | def norm(img): function check_size (line 40) | def check_size(): function rename (line 89) | def rename(): function check_direction (line 100) | def check_direction(): FILE: Finetune/Amos/gen_json.py function get_identifiers_from_splitted_files (line 6) | def get_identifiers_from_splitted_files(folder: str): function generate_dataset_json (line 11) | def generate_dataset_json(output_file: str, imagesTr_dir: str, imagesTs_... FILE: Finetune/Amos/inferers.py function double_sliding_window_inference (line 28) | def double_sliding_window_inference( function one_hot (line 294) | def one_hot(labels: torch.Tensor, num_classes: int, dtype: torch.dtype =... class GroupName (line 372) | class GroupName(enum.Enum): function get_transforms_func (line 413) | def get_transforms_func(views: TransformsType, function get_permute_transform (line 440) | def get_permute_transform(view_src: PermuteType, function permute_inverse (line 452) | def permute_inverse(xs: Sequence[torch.Tensor], function permute_rand (line 458) | def permute_rand( FILE: Finetune/Amos/main.py function main (line 112) | def main(): function main_worker (line 124) | def main_worker(gpu, args): function init_log (line 286) | def init_log(name, level=logging.INFO): FILE: Finetune/Amos/optimizers/lr_scheduler.py class _LRSchedulerMONAI (line 23) | class _LRSchedulerMONAI(_LRScheduler): method __init__ (line 27) | def __init__(self, optimizer: Optimizer, end_lr: float, num_iter: int,... class LinearLR (line 42) | class LinearLR(_LRSchedulerMONAI): method get_lr (line 47) | def get_lr(self): class ExponentialLR (line 52) | class ExponentialLR(_LRSchedulerMONAI): method get_lr (line 57) | def get_lr(self): class WarmupCosineSchedule (line 62) | class WarmupCosineSchedule(LambdaLR): method __init__ (line 67) | def __init__( method lr_lambda (line 85) | def lr_lambda(self, step): class LinearWarmupCosineAnnealingLR (line 92) | class LinearWarmupCosineAnnealingLR(_LRScheduler): method __init__ (line 93) | def __init__( method get_lr (line 118) | def get_lr(self) -> List[float]: method _get_closed_form_lr (line 156) | def _get_closed_form_lr(self) -> List[float]: FILE: Finetune/Amos/pre_cache.py function main (line 87) | def main(): FILE: Finetune/Amos/test.py function main (line 88) | def main(): FILE: Finetune/Amos/trainer.py function train_epoch (line 27) | def train_epoch(model, loader, optimizer, scaler, epoch, loss_func, args): function val_epoch (line 72) | def val_epoch(model, loader, epoch, acc_func, args, model_inferer=None, ... function save_checkpoint (line 121) | def save_checkpoint(model, epoch, args, filename="model.pt", best_acc=0,... function run_training (line 133) | def run_training( FILE: Finetune/Amos/utils/data_test.py class Sampler (line 22) | class Sampler(torch.utils.data.Sampler): method __init__ (line 23) | def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True... method __iter__ (line 43) | def __iter__(self): method __len__ (line 62) | def __len__(self): method set_epoch (line 65) | def set_epoch(self, epoch): function get_loader (line 69) | def get_loader(args): FILE: Finetune/Amos/utils/data_utils.py class Sampler (line 22) | class Sampler(torch.utils.data.Sampler): method __init__ (line 23) | def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True... method __iter__ (line 43) | def __iter__(self): method __len__ (line 62) | def __len__(self): method set_epoch (line 65) | def set_epoch(self, epoch): function get_loader (line 69) | def get_loader(args): FILE: Finetune/Amos/utils/utils.py function resample_3d (line 17) | def resample_3d(img, target_size): function dice (line 25) | def dice(x, y): class AverageMeter (line 34) | class AverageMeter(object): method __init__ (line 35) | def __init__(self): method reset (line 38) | def reset(self): method update (line 44) | def update(self, val, n=1): function distributed_all_gather (line 51) | def distributed_all_gather( function color_map (line 81) | def color_map(dataset='pascal'): function check_dir (line 126) | def check_dir(dir): FILE: Finetune/Amos/val.py function main (line 78) | def main(): FILE: Finetune/BTCV/main.py function main (line 114) | def main(): function main_worker (line 126) | def main_worker(gpu, args): function init_log (line 286) | def init_log(name, level=logging.INFO): FILE: Finetune/BTCV/optimizers/lr_scheduler.py class _LRSchedulerMONAI (line 23) | class _LRSchedulerMONAI(_LRScheduler): method __init__ (line 27) | def __init__(self, optimizer: Optimizer, end_lr: float, num_iter: int,... class LinearLR (line 42) | class LinearLR(_LRSchedulerMONAI): method get_lr (line 47) | def get_lr(self): class ExponentialLR (line 52) | class ExponentialLR(_LRSchedulerMONAI): method get_lr (line 57) | def get_lr(self): class WarmupCosineSchedule (line 62) | class WarmupCosineSchedule(LambdaLR): method __init__ (line 67) | def __init__( method lr_lambda (line 85) | def lr_lambda(self, step): class LinearWarmupCosineAnnealingLR (line 92) | class LinearWarmupCosineAnnealingLR(_LRScheduler): method __init__ (line 93) | def __init__( method get_lr (line 118) | def get_lr(self) -> List[float]: method _get_closed_form_lr (line 156) | def _get_closed_form_lr(self) -> List[float]: FILE: Finetune/BTCV/trainer.py function train_epoch (line 27) | def train_epoch(model, loader, optimizer, scheduler, scaler, epoch, loss... function val_epoch (line 75) | def val_epoch(model, loader, epoch, acc_func, args, model_inferer=None, ... function save_checkpoint (line 125) | def save_checkpoint(model, epoch, args, filename="model.pt", best_acc=0,... function run_training (line 137) | def run_training( FILE: Finetune/BTCV/utils/data_test.py class Sampler (line 22) | class Sampler(torch.utils.data.Sampler): method __init__ (line 23) | def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True... method __iter__ (line 43) | def __iter__(self): method __len__ (line 62) | def __len__(self): method set_epoch (line 65) | def set_epoch(self, epoch): function get_loader (line 69) | def get_loader(args): FILE: Finetune/BTCV/utils/data_utils.py class Sampler (line 22) | class Sampler(torch.utils.data.Sampler): method __init__ (line 23) | def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True... method __iter__ (line 43) | def __iter__(self): method __len__ (line 62) | def __len__(self): method set_epoch (line 65) | def set_epoch(self, epoch): function get_loader (line 69) | def get_loader(args): FILE: Finetune/BTCV/utils/utils.py function resample_3d (line 17) | def resample_3d(img, target_size): function dice (line 25) | def dice(x, y): class AverageMeter (line 34) | class AverageMeter(object): method __init__ (line 35) | def __init__(self): method reset (line 38) | def reset(self): method update (line 44) | def update(self, val, n=1): function distributed_all_gather (line 51) | def distributed_all_gather( FILE: Finetune/BTCV/val.py function main (line 78) | def main(): FILE: Finetune/CC-CCII/eval.py function main (line 83) | def main(): FILE: Finetune/CC-CCII/main.py function main (line 93) | def main(): function main_worker (line 105) | def main_worker(gpu, args): function init_log (line 228) | def init_log(name, level=logging.INFO): FILE: Finetune/CC-CCII/model.py class Swin (line 12) | class Swin(nn.Module): method __init__ (line 13) | def __init__(self, args): method forward (line 136) | def forward(self, x_in): FILE: Finetune/CC-CCII/optimizers/lr_scheduler.py class _LRSchedulerMONAI (line 23) | class _LRSchedulerMONAI(_LRScheduler): method __init__ (line 27) | def __init__(self, optimizer: Optimizer, end_lr: float, num_iter: int,... class LinearLR (line 42) | class LinearLR(_LRSchedulerMONAI): method get_lr (line 47) | def get_lr(self): class ExponentialLR (line 52) | class ExponentialLR(_LRSchedulerMONAI): method get_lr (line 57) | def get_lr(self): class WarmupCosineSchedule (line 62) | class WarmupCosineSchedule(LambdaLR): method __init__ (line 67) | def __init__( method lr_lambda (line 85) | def lr_lambda(self, step): class LinearWarmupCosineAnnealingLR (line 92) | class LinearWarmupCosineAnnealingLR(_LRScheduler): method __init__ (line 93) | def __init__( method get_lr (line 118) | def get_lr(self) -> List[float]: method _get_closed_form_lr (line 156) | def _get_closed_form_lr(self) -> List[float]: FILE: Finetune/CC-CCII/trainer.py function resize (line 27) | def resize(img): function train_epoch (line 39) | def train_epoch(model, loader, optimizer, scheduler, scaler, epoch, args): function val_epoch (line 84) | def val_epoch(model, loader, epoch, args): function save_checkpoint (line 119) | def save_checkpoint(model, epoch, args, filename="model.pt", best_acc=0,... function run_training (line 131) | def run_training( FILE: Finetune/CC-CCII/utils/data_utils.py function get_loader (line 24) | def get_loader(args): class CC_CCII (line 84) | class CC_CCII(torch.utils.data.Dataset): method __init__ (line 91) | def __init__(self, data=None, transforms=None, augmentation=True, args... method __getitem__ (line 103) | def __getitem__(self, index): method __len__ (line 139) | def __len__(self): FILE: Finetune/CC-CCII/utils/utils.py function resample_3d (line 17) | def resample_3d(img, target_size): function dice (line 25) | def dice(x, y): class AverageMeter (line 34) | class AverageMeter(object): method __init__ (line 35) | def __init__(self): method reset (line 38) | def reset(self): method update (line 44) | def update(self, val, n=1): function distributed_all_gather (line 51) | def distributed_all_gather( FILE: Finetune/Flare22/inferers.py function double_sliding_window_inference (line 28) | def double_sliding_window_inference( function one_hot (line 294) | def one_hot(labels: torch.Tensor, num_classes: int, dtype: torch.dtype =... class GroupName (line 372) | class GroupName(enum.Enum): function get_transforms_func (line 413) | def get_transforms_func(views: TransformsType, function get_permute_transform (line 440) | def get_permute_transform(view_src: PermuteType, function permute_inverse (line 452) | def permute_inverse(xs: Sequence[torch.Tensor], function permute_rand (line 458) | def permute_rand( FILE: Finetune/Flare22/main.py function main (line 112) | def main(): function main_worker (line 124) | def main_worker(gpu, args): function init_log (line 286) | def init_log(name, level=logging.INFO): FILE: Finetune/Flare22/optimizers/lr_scheduler.py class _LRSchedulerMONAI (line 23) | class _LRSchedulerMONAI(_LRScheduler): method __init__ (line 27) | def __init__(self, optimizer: Optimizer, end_lr: float, num_iter: int,... class LinearLR (line 42) | class LinearLR(_LRSchedulerMONAI): method get_lr (line 47) | def get_lr(self): class ExponentialLR (line 52) | class ExponentialLR(_LRSchedulerMONAI): method get_lr (line 57) | def get_lr(self): class WarmupCosineSchedule (line 62) | class WarmupCosineSchedule(LambdaLR): method __init__ (line 67) | def __init__( method lr_lambda (line 85) | def lr_lambda(self, step): class LinearWarmupCosineAnnealingLR (line 92) | class LinearWarmupCosineAnnealingLR(_LRScheduler): method __init__ (line 93) | def __init__( method get_lr (line 118) | def get_lr(self) -> List[float]: method _get_closed_form_lr (line 156) | def _get_closed_form_lr(self) -> List[float]: FILE: Finetune/Flare22/trainer.py function train_epoch (line 27) | def train_epoch(model, loader, optimizer, scaler, epoch, loss_func, args): function val_epoch (line 72) | def val_epoch(model, loader, epoch, acc_func, args, model_inferer=None, ... function save_checkpoint (line 121) | def save_checkpoint(model, epoch, args, filename="model.pt", best_acc=0,... function run_training (line 133) | def run_training( FILE: Finetune/Flare22/utils/data_test.py class Sampler (line 22) | class Sampler(torch.utils.data.Sampler): method __init__ (line 23) | def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True... method __iter__ (line 43) | def __iter__(self): method __len__ (line 62) | def __len__(self): method set_epoch (line 65) | def set_epoch(self, epoch): function get_loader (line 69) | def get_loader(args): FILE: Finetune/Flare22/utils/data_utils.py class Sampler (line 22) | class Sampler(torch.utils.data.Sampler): method __init__ (line 23) | def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True... method __iter__ (line 43) | def __iter__(self): method __len__ (line 62) | def __len__(self): method set_epoch (line 65) | def set_epoch(self, epoch): function get_loader (line 69) | def get_loader(args): FILE: Finetune/Flare22/utils/utils.py function resample_3d (line 17) | def resample_3d(img, target_size): function dice (line 25) | def dice(x, y): class AverageMeter (line 34) | class AverageMeter(object): method __init__ (line 35) | def __init__(self): method reset (line 38) | def reset(self): method update (line 44) | def update(self, val, n=1): function distributed_all_gather (line 51) | def distributed_all_gather( function color_map (line 81) | def color_map(dataset='pascal'): function check_dir (line 126) | def check_dir(dir): FILE: Finetune/Flare22/val.py function main (line 78) | def main(): FILE: Finetune/MM-WHS/inferers.py function double_sliding_window_inference (line 28) | def double_sliding_window_inference( function one_hot (line 294) | def one_hot(labels: torch.Tensor, num_classes: int, dtype: torch.dtype =... class GroupName (line 372) | class GroupName(enum.Enum): function get_transforms_func (line 413) | def get_transforms_func(views: TransformsType, function get_permute_transform (line 440) | def get_permute_transform(view_src: PermuteType, function permute_inverse (line 452) | def permute_inverse(xs: Sequence[torch.Tensor], function permute_rand (line 458) | def permute_rand( FILE: Finetune/MM-WHS/main.py function main (line 109) | def main(): function main_worker (line 121) | def main_worker(gpu, args): function init_log (line 278) | def init_log(name, level=logging.INFO): FILE: Finetune/MM-WHS/optimizers/lr_scheduler.py class _LRSchedulerMONAI (line 23) | class _LRSchedulerMONAI(_LRScheduler): method __init__ (line 27) | def __init__(self, optimizer: Optimizer, end_lr: float, num_iter: int,... class LinearLR (line 42) | class LinearLR(_LRSchedulerMONAI): method get_lr (line 47) | def get_lr(self): class ExponentialLR (line 52) | class ExponentialLR(_LRSchedulerMONAI): method get_lr (line 57) | def get_lr(self): class WarmupCosineSchedule (line 62) | class WarmupCosineSchedule(LambdaLR): method __init__ (line 67) | def __init__( method lr_lambda (line 85) | def lr_lambda(self, step): class LinearWarmupCosineAnnealingLR (line 92) | class LinearWarmupCosineAnnealingLR(_LRScheduler): method __init__ (line 93) | def __init__( method get_lr (line 118) | def get_lr(self) -> List[float]: method _get_closed_form_lr (line 156) | def _get_closed_form_lr(self) -> List[float]: FILE: Finetune/MM-WHS/test.py function get_test_loader (line 88) | def get_test_loader(args): function main (line 141) | def main(): FILE: Finetune/MM-WHS/trainer.py function train_epoch (line 27) | def train_epoch(model, loader, optimizer, scaler, epoch, loss_func, args): function val_epoch (line 72) | def val_epoch(model, loader, epoch, acc_func, args, model_inferer=None, ... function save_checkpoint (line 121) | def save_checkpoint(model, epoch, args, filename="model.pt", best_acc=0,... function run_training (line 133) | def run_training( FILE: Finetune/MM-WHS/utils/data_utils.py class Sampler (line 23) | class Sampler(torch.utils.data.Sampler): method __init__ (line 24) | def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True... method __iter__ (line 44) | def __iter__(self): method __len__ (line 63) | def __len__(self): method set_epoch (line 66) | def set_epoch(self, epoch): function get_loader (line 70) | def get_loader(args): class Convert_WHS_label (line 152) | class Convert_WHS_label(MapTransform): method __call__ (line 154) | def __call__(self, data): FILE: Finetune/MM-WHS/utils/utils.py function resample_3d (line 17) | def resample_3d(img, target_size): function dice (line 25) | def dice(x, y): class AverageMeter (line 34) | class AverageMeter(object): method __init__ (line 35) | def __init__(self): method reset (line 38) | def reset(self): method update (line 44) | def update(self, val, n=1): function distributed_all_gather (line 51) | def distributed_all_gather( function color_map (line 81) | def color_map(dataset='pascal'): function check_dir (line 126) | def check_dir(dir): function load (line 131) | def load(model, model_dict): FILE: Finetune/Word/main.py function main (line 112) | def main(): function main_worker (line 124) | def main_worker(gpu, args): function init_log (line 286) | def init_log(name, level=logging.INFO): FILE: Finetune/Word/optimizers/lr_scheduler.py class _LRSchedulerMONAI (line 23) | class _LRSchedulerMONAI(_LRScheduler): method __init__ (line 27) | def __init__(self, optimizer: Optimizer, end_lr: float, num_iter: int,... class LinearLR (line 42) | class LinearLR(_LRSchedulerMONAI): method get_lr (line 47) | def get_lr(self): class ExponentialLR (line 52) | class ExponentialLR(_LRSchedulerMONAI): method get_lr (line 57) | def get_lr(self): class WarmupCosineSchedule (line 62) | class WarmupCosineSchedule(LambdaLR): method __init__ (line 67) | def __init__( method lr_lambda (line 85) | def lr_lambda(self, step): class LinearWarmupCosineAnnealingLR (line 92) | class LinearWarmupCosineAnnealingLR(_LRScheduler): method __init__ (line 93) | def __init__( method get_lr (line 118) | def get_lr(self) -> List[float]: method _get_closed_form_lr (line 156) | def _get_closed_form_lr(self) -> List[float]: FILE: Finetune/Word/trainer.py function train_epoch (line 27) | def train_epoch(model, loader, optimizer, scheduler, scaler, epoch, loss... function val_epoch (line 75) | def val_epoch(model, loader, epoch, acc_func, args, model_inferer=None, ... function save_checkpoint (line 125) | def save_checkpoint(model, epoch, args, filename="model.pt", best_acc=0,... function run_training (line 137) | def run_training( FILE: Finetune/Word/utils/data_utils.py class Sampler (line 24) | class Sampler(torch.utils.data.Sampler): method __init__ (line 25) | def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True... method __iter__ (line 45) | def __iter__(self): method __len__ (line 64) | def __len__(self): method set_epoch (line 67) | def set_epoch(self, epoch): function get_loader_word (line 71) | def get_loader_word(args): FILE: Finetune/Word/utils/utils.py function resample_3d (line 17) | def resample_3d(img, target_size): function dice (line 25) | def dice(x, y): class AverageMeter (line 34) | class AverageMeter(object): method __init__ (line 35) | def __init__(self): method reset (line 38) | def reset(self): method update (line 44) | def update(self, val, n=1): function distributed_all_gather (line 51) | def distributed_all_gather( function color_map (line 81) | def color_map(dataset='pascal'): function check_dir (line 126) | def check_dir(dir): FILE: Finetune/nnUNet/nnunetv2/batch_running/collect_results_custom_Decathlon.py function collect_results (line 12) | def collect_results(trainers: dict, datasets: List, output_file: str, function summarize (line 43) | def summarize(input_file, output_file, folds: Tuple[int, ...], configs: ... FILE: Finetune/nnUNet/nnunetv2/batch_running/generate_lsf_runs_customDecathlon.py function merge (line 5) | def merge(dict1, dict2): FILE: Finetune/nnUNet/nnunetv2/batch_running/release_trainings/nnunetv2_v1/collect_results.py function collect_results (line 12) | def collect_results(trainers: dict, datasets: List, output_file: str, function summarize (line 43) | def summarize(input_file, output_file, folds: Tuple[int, ...], configs: ... FILE: Finetune/nnUNet/nnunetv2/batch_running/release_trainings/nnunetv2_v1/generate_lsf_commands.py function merge (line 5) | def merge(dict1, dict2): FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/Dataset027_ACDC.py function make_out_dirs (line 9) | def make_out_dirs(dataset_id: int, task_name="ACDC"): function copy_files (line 25) | def copy_files(src_data_folder: Path, train_dir: Path, labels_dir: Path,... function convert_acdc (line 51) | def convert_acdc(src_data_folder: str, dataset_id=27): FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/Dataset114_MNMs.py function read_csv (line 14) | def read_csv(csv_file: str): function convert_mnms (line 38) | def convert_mnms(src_data_folder: Path, csv_file_name: str, dataset_id: ... function save_cardiac_phases (line 64) | def save_cardiac_phases( function save_extracted_nifti_slice (line 81) | def save_extracted_nifti_slice(image, ed_frame: int, es_frame: int, out_... function create_custom_splits (line 96) | def create_custom_splits(src_data_folder: Path, csv_file: str, dataset_i... function get_vendor_split (line 132) | def get_vendor_split(patients: list[str], num_val_patients: int): class RawTextArgumentDefaultsHelpFormatter (line 142) | class RawTextArgumentDefaultsHelpFormatter(argparse.ArgumentDefaultsHelp... FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/Dataset115_EMIDEC.py function copy_files (line 8) | def copy_files(src_data_dir: Path, src_test_dir: Path, train_dir: Path, ... function convert_emidec (line 28) | def convert_emidec(src_data_dir: str, src_test_dir: str, dataset_id=27): FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/Dataset120_RoadSegmentation.py function load_and_covnert_case (line 14) | def load_and_covnert_case(input_image: str, input_seg: str, output_image... FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/Dataset137_BraTS21.py function copy_BraTS_segmentation_and_convert_labels_to_nnUNet (line 12) | def copy_BraTS_segmentation_and_convert_labels_to_nnUNet(in_file: str, o... function convert_labels_back_to_BraTS (line 32) | def convert_labels_back_to_BraTS(seg: np.ndarray): function load_convert_labels_back_to_BraTS (line 40) | def load_convert_labels_back_to_BraTS(filename, input_folder, output_fol... function convert_folder_with_preds_back_to_BraTS_labeling_convention (line 49) | def convert_folder_with_preds_back_to_BraTS_labeling_convention(input_fo... FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/Dataset218_Amos2022_task1.py function convert_amos_task1 (line 7) | def convert_amos_task1(amos_base_dir: str, nnunet_dataset_id: int = 218): FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/Dataset219_Amos2022_task2.py function convert_amos_task2 (line 7) | def convert_amos_task2(amos_base_dir: str, nnunet_dataset_id: int = 219): FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/Dataset220_KiTS2023.py function convert_kits2023 (line 7) | def convert_kits2023(kits_base_dir: str, nnunet_dataset_id: int = 220): FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/Dataset221_AutoPETII_2023.py function convert_autopet (line 7) | def convert_autopet(autopet_base_dir:str = '/media/isensee/My Book1/Auto... FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/convert_MSD_dataset.py function split_4d_nifti (line 14) | def split_4d_nifti(filename, output_folder): function convert_msd_dataset (line 41) | def convert_msd_dataset(source_folder: str, overwrite_target_id: Optiona... function entry_point (line 117) | def entry_point(): FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/convert_raw_dataset_from_old_nnunet_format.py function convert (line 8) | def convert(source_folder, target_dataset_name): function convert_entry_point (line 43) | def convert_entry_point(): FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/datasets_for_integration_tests/Dataset996_IntegrationTest_Hippocampus_regions_ignore.py function sparsify_segmentation (line 13) | def sparsify_segmentation(seg: np.ndarray, label_manager: LabelManager, ... FILE: Finetune/nnUNet/nnunetv2/dataset_conversion/generate_dataset_json.py function generate_dataset_json (line 6) | def generate_dataset_json(output_folder: str, FILE: Finetune/nnUNet/nnunetv2/ensembling/ensemble.py function average_probabilities (line 17) | def average_probabilities(list_of_files: List[str]) -> np.ndarray: function merge_files (line 32) | def merge_files(list_of_files, function ensemble_folders (line 49) | def ensemble_folders(list_of_input_folders: List[str], function entry_point_ensemble_folders (line 114) | def entry_point_ensemble_folders(): function ensemble_crossvalidations (line 128) | def ensemble_crossvalidations(list_of_trained_model_folders: List[str], FILE: Finetune/nnUNet/nnunetv2/evaluation/accumulate_cv_results.py function accumulate_cv_results (line 12) | def accumulate_cv_results(trained_model_folder, FILE: Finetune/nnUNet/nnunetv2/evaluation/evaluate_predictions.py function label_or_region_to_key (line 20) | def label_or_region_to_key(label_or_region: Union[int, Tuple[int]]): function key_to_label_or_region (line 24) | def key_to_label_or_region(key: str): function save_summary_json (line 34) | def save_summary_json(results: dict, output_file: str): function load_summary_json (line 51) | def load_summary_json(filename: str): function labels_to_list_of_regions (line 63) | def labels_to_list_of_regions(labels: List[int]): function region_or_label_to_mask (line 67) | def region_or_label_to_mask(segmentation: np.ndarray, region_or_label: U... function compute_tp_fp_fn_tn (line 77) | def compute_tp_fp_fn_tn(mask_ref: np.ndarray, mask_pred: np.ndarray, ign... function compute_metrics (line 89) | def compute_metrics(reference_file: str, prediction_file: str, image_rea... function compute_metrics_on_folder (line 123) | def compute_metrics_on_folder(folder_ref: str, folder_pred: str, output_... function compute_metrics_on_folder2 (line 179) | def compute_metrics_on_folder2(folder_ref: str, folder_pred: str, datase... function compute_metrics_on_folder_simple (line 201) | def compute_metrics_on_folder_simple(folder_ref: str, folder_pred: str, ... function evaluate_folder_entry_point (line 217) | def evaluate_folder_entry_point(): function evaluate_simple_entry_point (line 235) | def evaluate_simple_entry_point(): FILE: Finetune/nnUNet/nnunetv2/evaluation/find_best_configuration.py function filter_available_models (line 26) | def filter_available_models(model_dict: Union[List[dict], Tuple[dict, ..... function generate_inference_command (line 51) | def generate_inference_command(dataset_name_or_id: Union[int, str], conf... function find_best_configuration (line 81) | def find_best_configuration(dataset_name_or_id, function print_inference_instructions (line 214) | def print_inference_instructions(inference_info_dict: dict, instructions... function dumb_trainer_config_plans_to_trained_models_dict (line 257) | def dumb_trainer_config_plans_to_trained_models_dict(trainers: List[str]... function find_best_configuration_entry_point (line 271) | def find_best_configuration_entry_point(): function accumulate_crossval_results_entry_point (line 300) | def accumulate_crossval_results_entry_point(): FILE: Finetune/nnUNet/nnunetv2/experiment_planning/dataset_fingerprint/fingerprint_extractor.py class DatasetFingerprintExtractor (line 18) | class DatasetFingerprintExtractor(object): method __init__ (line 19) | def __init__(self, dataset_name_or_id: Union[str, int], num_processes:... method collect_foreground_intensities (line 42) | def collect_foreground_intensities(segmentation: np.ndarray, images: n... method analyze_case (line 83) | def analyze_case(image_files: List[str], segmentation_file: str, reade... method run (line 107) | def run(self, overwrite_existing: bool = False) -> dict: FILE: Finetune/nnUNet/nnunetv2/experiment_planning/experiment_planners/default_experiment_planner.py class ExperimentPlanner (line 24) | class ExperimentPlanner(object): method __init__ (line 25) | def __init__(self, dataset_name_or_id: Union[str, int], method determine_reader_writer (line 82) | def determine_reader_writer(self): method static_estimate_VRAM_usage (line 88) | def static_estimate_VRAM_usage(patch_size: Tuple[int], method determine_resampling (line 114) | def determine_resampling(self, *args, **kwargs): method determine_segmentation_softmax_export_fn (line 138) | def determine_segmentation_softmax_export_fn(self, *args, **kwargs): method determine_fullres_target_spacing (line 156) | def determine_fullres_target_spacing(self) -> np.ndarray: method determine_normalization_scheme_and_whether_mask_is_used_for_norm (line 199) | def determine_normalization_scheme_and_whether_mask_is_used_for_norm(s... method determine_transpose (line 216) | def determine_transpose(self): method get_plans_for_configuration (line 229) | def get_plans_for_configuration(self, method plan_experiment (line 371) | def plan_experiment(self): method save_plans (line 502) | def save_plans(self, plans): method generate_data_identifier (line 521) | def generate_data_identifier(self, configuration_name: str) -> str: method load_plans (line 529) | def load_plans(self, fname: str): FILE: Finetune/nnUNet/nnunetv2/experiment_planning/experiment_planners/network_topology.py function get_shape_must_be_divisible_by (line 5) | def get_shape_must_be_divisible_by(net_numpool_per_axis): function pad_shape (line 9) | def pad_shape(shape, must_be_divisible_by): function get_pool_and_conv_props (line 30) | def get_pool_and_conv_props(spacing, patch_size, min_feature_map_size, m... FILE: Finetune/nnUNet/nnunetv2/experiment_planning/experiment_planners/resencUNet_planner.py class ResEncUNetPlanner (line 9) | class ResEncUNetPlanner(ExperimentPlanner): method __init__ (line 10) | def __init__(self, dataset_name_or_id: Union[str, int], FILE: Finetune/nnUNet/nnunetv2/experiment_planning/plan_and_preprocess_api.py function extract_fingerprint_dataset (line 18) | def extract_fingerprint_dataset(dataset_id: int, function extract_fingerprints (line 36) | def extract_fingerprints(dataset_ids: List[int], fingerprint_extractor_c... function plan_experiment_dataset (line 51) | def plan_experiment_dataset(dataset_id: int, function plan_experiments (line 72) | def plan_experiments(dataset_ids: List[int], experiment_planner_class_na... function preprocess_dataset (line 87) | def preprocess_dataset(dataset_id: int, function preprocess (line 132) | def preprocess(dataset_ids: List[int], FILE: Finetune/nnUNet/nnunetv2/experiment_planning/plan_and_preprocess_entrypoints.py function extract_fingerprint_entry (line 5) | def extract_fingerprint_entry(): function plan_experiment_entry (line 30) | def plan_experiment_entry(): function preprocess_entry (line 69) | def preprocess_entry(): function plan_and_preprocess_entry (line 109) | def plan_and_preprocess_entry(): FILE: Finetune/nnUNet/nnunetv2/experiment_planning/plans_for_pretraining/move_plans_between_datasets.py function move_plans_between_datasets (line 13) | def move_plans_between_datasets( function entry_point_move_plans_between_datasets (line 65) | def entry_point_move_plans_between_datasets(): FILE: Finetune/nnUNet/nnunetv2/experiment_planning/verify_dataset_integrity.py function verify_labels (line 32) | def verify_labels(label_file: str, readerclass: Type[BaseReaderWriter], ... function check_cases (line 47) | def check_cases(image_files: List[str], label_file: str, expected_num_ch... function verify_dataset_integrity (line 119) | def verify_dataset_integrity(folder: str, num_processes: int = 8) -> None: FILE: Finetune/nnUNet/nnunetv2/imageio/base_reader_writer.py class BaseReaderWriter (line 21) | class BaseReaderWriter(ABC): method _check_all_same (line 23) | def _check_all_same(input_list): method _check_all_same_array (line 31) | def _check_all_same_array(input_list): method read_images (line 39) | def read_images(self, image_fnames: Union[List[str], Tuple[str, ...]])... method read_seg (line 72) | def read_seg(self, seg_fname: str) -> Tuple[np.ndarray, dict]: method write_seg (line 89) | def write_seg(self, seg: np.ndarray, output_fname: str, properties: di... FILE: Finetune/nnUNet/nnunetv2/imageio/natural_image_reader_writer.py class NaturalImage2DIO (line 22) | class NaturalImage2DIO(BaseReaderWriter): method read_images (line 36) | def read_images(self, image_fnames: Union[List[str], Tuple[str, ...]])... method read_seg (line 61) | def read_seg(self, seg_fname: str) -> Tuple[np.ndarray, dict]: method write_seg (line 64) | def write_seg(self, seg: np.ndarray, output_fname: str, properties: di... FILE: Finetune/nnUNet/nnunetv2/imageio/nibabel_reader_writer.py class NibabelIO (line 24) | class NibabelIO(BaseReaderWriter): method read_images (line 37) | def read_images(self, image_fnames: Union[List[str], Tuple[str, ...]])... method read_seg (line 90) | def read_seg(self, seg_fname: str) -> Tuple[np.ndarray, dict]: method write_seg (line 93) | def write_seg(self, seg: np.ndarray, output_fname: str, properties: di... class NibabelIOWithReorient (line 100) | class NibabelIOWithReorient(BaseReaderWriter): method read_images (line 115) | def read_images(self, image_fnames: Union[List[str], Tuple[str, ...]])... method read_seg (line 173) | def read_seg(self, seg_fname: str) -> Tuple[np.ndarray, dict]: method write_seg (line 176) | def write_seg(self, seg: np.ndarray, output_fname: str, properties: di... FILE: Finetune/nnUNet/nnunetv2/imageio/reader_writer_registry.py function determine_reader_writer_from_dataset_json (line 23) | def determine_reader_writer_from_dataset_json(dataset_json_content: dict... function determine_reader_writer_from_file_ending (line 41) | def determine_reader_writer_from_file_ending(file_ending: str, example_f... function recursive_find_reader_writer_by_name (line 73) | def recursive_find_reader_writer_by_name(rw_class_name: str) -> Type[Bas... FILE: Finetune/nnUNet/nnunetv2/imageio/simpleitk_reader_writer.py class SimpleITKIO (line 22) | class SimpleITKIO(BaseReaderWriter): method read_images (line 29) | def read_images(self, image_fnames: Union[List[str], Tuple[str, ...]])... method read_seg (line 114) | def read_seg(self, seg_fname: str) -> Tuple[np.ndarray, dict]: method write_seg (line 117) | def write_seg(self, seg: np.ndarray, output_fname: str, properties: di... FILE: Finetune/nnUNet/nnunetv2/imageio/tif_reader_writer.py class Tiff3DIO (line 23) | class Tiff3DIO(BaseReaderWriter): method read_images (line 38) | def read_images(self, image_fnames: Union[List[str], Tuple[str, ...]])... method write_seg (line 71) | def write_seg(self, seg: np.ndarray, output_fname: str, properties: di... method read_seg (line 79) | def read_seg(self, seg_fname: str) -> Tuple[np.ndarray, dict]: FILE: Finetune/nnUNet/nnunetv2/inference/data_iterators.py function preprocess_fromfiles_save_to_queue (line 17) | def preprocess_fromfiles_save_to_queue(list_of_lists: List[List[str]], function preprocessing_iterator_fromfiles (line 60) | def preprocessing_iterator_fromfiles(list_of_lists: List[List[str]], class PreprocessAdapter (line 119) | class PreprocessAdapter(DataLoader): method __init__ (line 120) | def __init__(self, list_of_lists: List[List[str]], method generate_train_batch (line 145) | def generate_train_batch(self): class PreprocessAdapterFromNpy (line 165) | class PreprocessAdapterFromNpy(DataLoader): method __init__ (line 166) | def __init__(self, list_of_images: List[np.ndarray], method generate_train_batch (line 191) | def generate_train_batch(self): function preprocess_fromnpy_save_to_queue (line 213) | def preprocess_fromnpy_save_to_queue(list_of_images: List[np.ndarray], function preprocessing_iterator_fromnpy (line 258) | def preprocessing_iterator_fromnpy(list_of_images: List[np.ndarray], FILE: Finetune/nnUNet/nnunetv2/inference/examples.py function my_iterator (line 89) | def my_iterator(list_of_input_arrs, list_of_input_props): FILE: Finetune/nnUNet/nnunetv2/inference/export_prediction.py function convert_predicted_logits_to_segmentation_with_correct_shape (line 15) | def convert_predicted_logits_to_segmentation_with_correct_shape(predicte... function export_prediction_from_logits (line 71) | def export_prediction_from_logits(predicted_array_or_file: Union[np.ndar... function resample_and_save (line 109) | def resample_and_save(predicted: Union[torch.Tensor, np.ndarray], target... FILE: Finetune/nnUNet/nnunetv2/inference/predict_from_raw_data.py class nnUNetPredictor (line 38) | class nnUNetPredictor(object): method __init__ (line 39) | def __init__(self, method initialize_from_trained_model_folder (line 68) | def initialize_from_trained_model_folder(self, model_training_output_d... method manual_initialization (line 117) | def manual_initialization(self, network: nn.Module, plans_manager: Pla... method auto_detect_available_folds (line 142) | def auto_detect_available_folds(model_training_output_dir, checkpoint_... method _manage_input_and_output_lists (line 151) | def _manage_input_and_output_lists(self, list_of_lists_or_source_folde... method predict_from_files (line 191) | def predict_from_files(self, method _internal_get_data_iterator_from_lists_of_filenames (line 252) | def _internal_get_data_iterator_from_lists_of_filenames(self, method get_data_iterator_from_raw_npy_data (line 275) | def get_data_iterator_from_raw_npy_data(self, method predict_from_list_of_npy_arrays (line 314) | def predict_from_list_of_npy_arrays(self, method predict_from_data_iterator (line 332) | def predict_from_data_iterator(self, method predict_single_npy_array (line 412) | def predict_single_npy_array(self, input_image: np.ndarray, image_prop... method predict_logits_from_preprocessed_data (line 449) | def predict_logits_from_preprocessed_data(self, data: torch.Tensor) ->... method _internal_get_sliding_window_slicers (line 509) | def _internal_get_sliding_window_slicers(self, image_size: Tuple[int, ... method _internal_maybe_mirror_and_predict (line 543) | def _internal_maybe_mirror_and_predict(self, x: torch.Tensor) -> torch... method predict_sliding_window_return_logits (line 560) | def predict_sliding_window_return_logits(self, input_image: torch.Tens... function predict_entry_point_modelfolder (line 639) | def predict_entry_point_modelfolder(): function predict_entry_point (line 728) | def predict_entry_point(): FILE: Finetune/nnUNet/nnunetv2/inference/sliding_window_prediction.py function compute_gaussian (line 11) | def compute_gaussian(tile_size: Union[Tuple[int, ...], List[int]], sigma... function compute_steps_for_sliding_window (line 32) | def compute_steps_for_sliding_window(image_size: Tuple[int, ...], tile_s... FILE: Finetune/nnUNet/nnunetv2/model_sharing/entry_points.py function print_license_warning (line 6) | def print_license_warning(): function download_by_url (line 18) | def download_by_url(): function install_from_zip_entry_point (line 31) | def install_from_zip_entry_point(): function export_pretrained_model_entry (line 41) | def export_pretrained_model_entry(): FILE: Finetune/nnUNet/nnunetv2/model_sharing/model_download.py function download_and_install_from_url (line 11) | def download_and_install_from_url(url): function download_file (line 37) | def download_file(url: str, local_filename: str, chunk_size: Optional[in... FILE: Finetune/nnUNet/nnunetv2/model_sharing/model_export.py function export_pretrained_model (line 6) | def export_pretrained_model(dataset_name_or_id: Union[int, str], output_... FILE: Finetune/nnUNet/nnunetv2/model_sharing/model_import.py function install_model_from_zip_file (line 6) | def install_model_from_zip_file(zip_file: str): FILE: Finetune/nnUNet/nnunetv2/postprocessing/remove_connected_components.py function remove_all_but_largest_component_from_segmentation (line 22) | def remove_all_but_largest_component_from_segmentation(segmentation: np.... function apply_postprocessing (line 37) | def apply_postprocessing(segmentation: np.ndarray, pp_fns: List[Callable... function load_postprocess_save (line 43) | def load_postprocess_save(segmentation_file: str, function determine_postprocessing (line 53) | def determine_postprocessing(folder_predictions: str, function apply_postprocessing_to_folder (line 248) | def apply_postprocessing_to_folder(input_folder: str, function entry_point_determine_postprocessing_folder (line 298) | def entry_point_determine_postprocessing_folder(): function entry_point_apply_postprocessing (line 318) | def entry_point_apply_postprocessing(): FILE: Finetune/nnUNet/nnunetv2/preprocessing/cropping/cropping.py function create_nonzero_mask (line 8) | def create_nonzero_mask(data): function crop_to_nonzero (line 24) | def crop_to_nonzero(data, seg=None, nonzero_label=-1): FILE: Finetune/nnUNet/nnunetv2/preprocessing/normalization/default_normalization_schemes.py class ImageNormalization (line 8) | class ImageNormalization(ABC): method __init__ (line 11) | def __init__(self, use_mask_for_norm: bool = None, intensityproperties... method run (line 20) | def run(self, image: np.ndarray, seg: np.ndarray = None) -> np.ndarray: class ZScoreNormalization (line 27) | class ZScoreNormalization(ImageNormalization): method run (line 30) | def run(self, image: np.ndarray, seg: np.ndarray = None) -> np.ndarray: class CTNormalization (line 52) | class CTNormalization(ImageNormalization): method run (line 55) | def run(self, image: np.ndarray, seg: np.ndarray = None) -> np.ndarray: class NoNormalization (line 67) | class NoNormalization(ImageNormalization): method run (line 70) | def run(self, image: np.ndarray, seg: np.ndarray = None) -> np.ndarray: class RescaleTo01Normalization (line 74) | class RescaleTo01Normalization(ImageNormalization): method run (line 77) | def run(self, image: np.ndarray, seg: np.ndarray = None) -> np.ndarray: class RGBTo01Normalization (line 84) | class RGBTo01Normalization(ImageNormalization): method run (line 87) | def run(self, image: np.ndarray, seg: np.ndarray = None) -> np.ndarray: FILE: Finetune/nnUNet/nnunetv2/preprocessing/normalization/map_channel_name_to_normalization.py function get_normalization_scheme (line 15) | def get_normalization_scheme(channel_name: str) -> Type[ImageNormalizati... FILE: Finetune/nnUNet/nnunetv2/preprocessing/preprocessors/default_preprocessor.py class DefaultPreprocessor (line 33) | class DefaultPreprocessor(object): method __init__ (line 34) | def __init__(self, verbose: bool = True): method run_case_npy (line 40) | def run_case_npy(self, data: np.ndarray, seg: Union[np.ndarray, None],... method run_case (line 115) | def run_case(self, image_files: List[str], seg_file: Union[str, None],... method run_case_save (line 143) | def run_case_save(self, output_filename_truncated: str, image_files: L... method _sample_foreground_locations (line 152) | def _sample_foreground_locations(seg: np.ndarray, classes_or_regions: ... method _normalize (line 180) | def _normalize(self, data: np.ndarray, seg: np.ndarray, configuration_... method run (line 194) | def run(self, dataset_name_or_id: Union[int, str], configuration_name:... method modify_seg_fn (line 259) | def modify_seg_fn(self, seg: np.ndarray, plans_manager: PlansManager, ... function example_test_case_preprocessing (line 267) | def example_test_case_preprocessing(): FILE: Finetune/nnUNet/nnunetv2/preprocessing/resampling/default_resampling.py function get_do_separate_z (line 13) | def get_do_separate_z(spacing: Union[Tuple[float, ...], List[float], np.... function get_lowres_axis (line 18) | def get_lowres_axis(new_spacing: Union[Tuple[float, ...], List[float], n... function compute_new_shape (line 23) | def compute_new_shape(old_shape: Union[Tuple[int, ...], List[int], np.nd... function resample_data_or_seg_to_spacing (line 32) | def resample_data_or_seg_to_spacing(data: np.ndarray, function resample_data_or_seg_to_shape (line 77) | def resample_data_or_seg_to_shape(data: Union[torch.Tensor, np.ndarray], function resample_data_or_seg (line 125) | def resample_data_or_seg(data: np.ndarray, new_shape: Union[Tuple[float,... FILE: Finetune/nnUNet/nnunetv2/preprocessing/resampling/utils.py function recursive_find_resampling_fn_by_name (line 8) | def recursive_find_resampling_fn_by_name(resampling_fn: str) -> Callable: FILE: Finetune/nnUNet/nnunetv2/run/load_pretrained_weights.py function load_pretrained_weights (line 6) | def load_pretrained_weights(network, fname, verbose=False): FILE: Finetune/nnUNet/nnunetv2/run/run_training.py function find_free_network_port (line 18) | def find_free_network_port() -> int: function get_trainer_from_args (line 31) | def get_trainer_from_args(dataset_name_or_id: Union[int, str], function maybe_load_checkpoint (line 70) | def maybe_load_checkpoint(nnunet_trainer: nnUNetTrainer, continue_traini... function setup_ddp (line 101) | def setup_ddp(rank, world_size): function cleanup_ddp (line 106) | def cleanup_ddp(): function run_ddp (line 110) | def run_ddp(rank, dataset_name_or_id, configuration, fold, tr, p, use_co... function run_training (line 138) | def run_training(dataset_name_or_id: Union[str, int], function run_training_entry (line 211) | def run_training_entry(): FILE: Finetune/nnUNet/nnunetv2/training/data_augmentation/compute_initial_patch_size.py function get_patch_size (line 4) | def get_patch_size(final_patch_size, rot_x, rot_y, rot_z, scale_range): FILE: Finetune/nnUNet/nnunetv2/training/data_augmentation/custom_transforms/cascade_transforms.py class MoveSegAsOneHotToData (line 10) | class MoveSegAsOneHotToData(AbstractTransform): method __init__ (line 11) | def __init__(self, index_in_origin: int, all_labels: Union[Tuple[int, ... method __call__ (line 23) | def __call__(self, **data_dict): class RemoveRandomConnectedComponentFromOneHotEncodingTransform (line 40) | class RemoveRandomConnectedComponentFromOneHotEncodingTransform(Abstract... method __init__ (line 41) | def __init__(self, channel_idx: Union[int, List[int]], key: str = "dat... method __call__ (line 58) | def __call__(self, **data_dict): class ApplyRandomBinaryOperatorTransform (line 88) | class ApplyRandomBinaryOperatorTransform(AbstractTransform): method __init__ (line 89) | def __init__(self, method __call__ (line 111) | def __call__(self, **data_dict): FILE: Finetune/nnUNet/nnunetv2/training/data_augmentation/custom_transforms/deep_supervision_donwsampling.py class DownsampleSegForDSTransform2 (line 8) | class DownsampleSegForDSTransform2(AbstractTransform): method __init__ (line 12) | def __init__(self, ds_scales: Union[List, Tuple], method __call__ (line 27) | def __call__(self, **data_dict): FILE: Finetune/nnUNet/nnunetv2/training/data_augmentation/custom_transforms/limited_length_multithreaded_augmenter.py class LimitedLenWrapper (line 4) | class LimitedLenWrapper(NonDetMultiThreadedAugmenter): method __init__ (line 5) | def __init__(self, my_imaginary_length, *args, **kwargs): method __len__ (line 9) | def __len__(self): FILE: Finetune/nnUNet/nnunetv2/training/data_augmentation/custom_transforms/manipulating_data_dict.py class RemoveKeyTransform (line 4) | class RemoveKeyTransform(AbstractTransform): method __init__ (line 5) | def __init__(self, key_to_remove: str): method __call__ (line 8) | def __call__(self, **data_dict): FILE: Finetune/nnUNet/nnunetv2/training/data_augmentation/custom_transforms/masking.py class MaskTransform (line 6) | class MaskTransform(AbstractTransform): method __init__ (line 7) | def __init__(self, apply_to_channels: List[int], mask_idx_in_seg: int ... method __call__ (line 18) | def __call__(self, **data_dict): FILE: Finetune/nnUNet/nnunetv2/training/data_augmentation/custom_transforms/region_based_training.py class ConvertSegmentationToRegionsTransform (line 7) | class ConvertSegmentationToRegionsTransform(AbstractTransform): method __init__ (line 8) | def __init__(self, regions: Union[List, Tuple], method __call__ (line 23) | def __call__(self, **data_dict): FILE: Finetune/nnUNet/nnunetv2/training/data_augmentation/custom_transforms/transforms_for_dummy_2d.py class Convert3DTo2DTransform (line 6) | class Convert3DTo2DTransform(AbstractTransform): method __init__ (line 7) | def __init__(self, apply_to_keys: Union[List[str], Tuple[str]] = ('dat... method __call__ (line 13) | def __call__(self, **data_dict): class Convert2DTo3DTransform (line 26) | class Convert2DTo3DTransform(AbstractTransform): method __init__ (line 27) | def __init__(self, apply_to_keys: Union[List[str], Tuple[str]] = ('dat... method __call__ (line 33) | def __call__(self, **data_dict): FILE: Finetune/nnUNet/nnunetv2/training/dataloading/base_data_loader.py class nnUNetDataLoaderBase (line 10) | class nnUNetDataLoaderBase(DataLoader): method __init__ (line 11) | def __init__(self, method _oversample_last_XX_percent (line 45) | def _oversample_last_XX_percent(self, sample_idx: int) -> bool: method _probabilistic_oversampling (line 51) | def _probabilistic_oversampling(self, sample_idx: int) -> bool: method determine_shapes (line 55) | def determine_shapes(self): method get_bbox (line 64) | def get_bbox(self, data_shape: np.ndarray, force_fg: bool, class_locat... FILE: Finetune/nnUNet/nnunetv2/training/dataloading/data_loader_2d.py class nnUNetDataLoader2D (line 6) | class nnUNetDataLoader2D(nnUNetDataLoaderBase): method generate_train_batch (line 7) | def generate_train_batch(self): FILE: Finetune/nnUNet/nnunetv2/training/dataloading/data_loader_3d.py class nnUNetDataLoader3D (line 6) | class nnUNetDataLoader3D(nnUNetDataLoaderBase): method generate_train_batch (line 7) | def generate_train_batch(self): FILE: Finetune/nnUNet/nnunetv2/training/dataloading/nnunet_dataset.py class nnUNetDataset (line 11) | class nnUNetDataset(object): method __init__ (line 12) | def __init__(self, folder: str, case_identifiers: List[str] = None, method __getitem__ (line 59) | def __getitem__(self, key): method __setitem__ (line 65) | def __setitem__(self, key, value): method keys (line 68) | def keys(self): method __len__ (line 71) | def __len__(self): method items (line 74) | def items(self): method values (line 77) | def values(self): method load_case (line 80) | def load_case(self, key): FILE: Finetune/nnUNet/nnunetv2/training/dataloading/utils.py function find_broken_image_and_labels (line 13) | def find_broken_image_and_labels( function try_fix_broken_npy (line 42) | def try_fix_broken_npy(path_do_data_dir: Path, case_ids: set[str], fix_i... function verify_or_stratify_npys (line 68) | def verify_or_stratify_npys(path_to_data_dir: str | Path) -> None: function _convert_to_npy (line 91) | def _convert_to_npy(npz_file: str, unpack_segmentation: bool = True, ove... function unpack_dataset (line 106) | def unpack_dataset(folder: str, unpack_segmentation: bool = True, overwr... function get_case_identifiers (line 119) | def get_case_identifiers(folder: str) -> List[str]: FILE: Finetune/nnUNet/nnunetv2/training/logging/nnunet_logger.py class nnUNetLogger (line 9) | class nnUNetLogger(object): method __init__ (line 17) | def __init__(self, verbose: bool = False): method log (line 31) | def log(self, key, value, epoch: int): method plot_progress_png (line 54) | def plot_progress_png(self, output_folder): method get_checkpoint (line 99) | def get_checkpoint(self): method load_checkpoint (line 102) | def load_checkpoint(self, checkpoint: dict): FILE: Finetune/nnUNet/nnunetv2/training/loss/compound_losses.py class DC_and_CE_loss (line 8) | class DC_and_CE_loss(nn.Module): method __init__ (line 9) | def __init__(self, soft_dice_kwargs, ce_kwargs, weight_ce=1, weight_di... method forward (line 31) | def forward(self, net_output: torch.Tensor, target: torch.Tensor): class DC_and_BCE_loss (line 59) | class DC_and_BCE_loss(nn.Module): method __init__ (line 60) | def __init__(self, bce_kwargs, soft_dice_kwargs, weight_ce=1, weight_d... method forward (line 83) | def forward(self, net_output: torch.Tensor, target: torch.Tensor): class DC_and_topk_loss (line 102) | class DC_and_topk_loss(nn.Module): method __init__ (line 103) | def __init__(self, soft_dice_kwargs, ce_kwargs, weight_ce=1, weight_di... method forward (line 124) | def forward(self, net_output: torch.Tensor, target: torch.Tensor): FILE: Finetune/nnUNet/nnunetv2/training/loss/deep_supervision.py class DeepSupervisionWrapper (line 5) | class DeepSupervisionWrapper(nn.Module): method __init__ (line 6) | def __init__(self, loss, weight_factors=None): method forward (line 19) | def forward(self, *args): FILE: Finetune/nnUNet/nnunetv2/training/loss/dice.py class SoftDiceLoss (line 8) | class SoftDiceLoss(nn.Module): method __init__ (line 9) | def __init__(self, apply_nonlin: Callable = None, batch_dice: bool = F... method forward (line 22) | def forward(self, x, y, loss_mask=None): class MemoryEfficientSoftDiceLoss (line 58) | class MemoryEfficientSoftDiceLoss(nn.Module): method __init__ (line 59) | def __init__(self, apply_nonlin: Callable = None, batch_dice: bool = F... method forward (line 72) | def forward(self, x, y, loss_mask=None): function get_tp_fp_fn_tn (line 122) | def get_tp_fp_fn_tn(net_output, gt, axes=None, mask=None, square=False): FILE: Finetune/nnUNet/nnunetv2/training/loss/robust_ce_loss.py class RobustCrossEntropyLoss (line 6) | class RobustCrossEntropyLoss(nn.CrossEntropyLoss): method forward (line 12) | def forward(self, input: Tensor, target: Tensor) -> Tensor: class TopKLoss (line 19) | class TopKLoss(RobustCrossEntropyLoss): method __init__ (line 23) | def __init__(self, weight=None, ignore_index: int = -100, k: float = 1... method forward (line 27) | def forward(self, inp, target): FILE: Finetune/nnUNet/nnunetv2/training/lr_scheduler/polylr.py class PolyLRScheduler (line 4) | class PolyLRScheduler(_LRScheduler): method __init__ (line 5) | def __init__(self, optimizer, initial_lr: float, max_steps: int, expon... method step (line 13) | def step(self, current_step=None): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py class nnUNetTrainer (line 67) | class nnUNetTrainer(object): method __init__ (line 68) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... method initialize (line 200) | def initialize(self): method _do_i_compile (line 229) | def _do_i_compile(self): method _save_debug_information (line 232) | def _save_debug_information(self): method build_network_architecture (line 268) | def build_network_architecture(plans_manager: PlansManager, method _get_deep_supervision_scales (line 295) | def _get_deep_supervision_scales(self): method _set_batch_size_and_oversample (line 303) | def _set_batch_size_and_oversample(self): method _build_loss (line 350) | def _build_loss(self): method configure_rotation_dummyDA_mirroring_and_inital_patch_size (line 376) | def configure_rotation_dummyDA_mirroring_and_inital_patch_size(self): method print_to_log_file (line 433) | def print_to_log_file(self, *args, also_print_to_console=True, add_tim... method print_plans (line 461) | def print_plans(self): method configure_optimizers (line 470) | def configure_optimizers(self): method plot_network_architecture (line 476) | def plot_network_architecture(self): method do_split (line 514) | def do_split(self): method get_tr_and_val_datasets (line 578) | def get_tr_and_val_datasets(self): method get_dataloaders (line 592) | def get_dataloaders(self): method get_plain_dataloaders (line 643) | def get_plain_dataloaders(self, initial_patch_size: Tuple[int, ...], d... method get_training_transforms (line 675) | def get_training_transforms( method get_validation_transforms (line 769) | def get_validation_transforms( method set_deep_supervision_enabled (line 798) | def set_deep_supervision_enabled(self, enabled: bool): method on_train_start (line 808) | def on_train_start(self): method on_train_end (line 850) | def on_train_end(self): method on_train_epoch_start (line 874) | def on_train_epoch_start(self): method train_step (line 884) | def train_step(self, batch: dict) -> dict: method on_train_epoch_end (line 916) | def on_train_epoch_end(self, train_outputs: List[dict]): method on_validation_epoch_start (line 928) | def on_validation_epoch_start(self): method validation_step (line 931) | def validation_step(self, batch: dict) -> dict: method on_validation_epoch_end (line 995) | def on_validation_epoch_end(self, val_outputs: List[dict]): method on_epoch_start (line 1028) | def on_epoch_start(self): method on_epoch_end (line 1031) | def on_epoch_end(self): method save_checkpoint (line 1057) | def save_checkpoint(self, filename: str) -> None: method load_checkpoint (line 1082) | def load_checkpoint(self, filename_or_checkpoint: Union[dict, str]) ->... method perform_actual_validation (line 1120) | def perform_actual_validation(self, save_probabilities: bool = False): method run_training (line 1249) | def run_training(self): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/nnUNetTrainer_swin.py class nnUNetTrainer_swin (line 12) | class nnUNetTrainer_swin(nnUNetTrainer): method __init__ (line 13) | def __init__( method build_network_architecture (line 27) | def build_network_architecture(plans_manager: PlansManager, method set_deep_supervision_enabled (line 66) | def set_deep_supervision_enabled(self, enabled: bool): class nnUNetTrainer_swin_pre (line 70) | class nnUNetTrainer_swin_pre(nnUNetTrainer): method __init__ (line 71) | def __init__( method build_network_architecture (line 85) | def build_network_architecture(plans_manager: PlansManager, method set_deep_supervision_enabled (line 149) | def set_deep_supervision_enabled(self, enabled: bool): function delete_patch_embed (line 153) | def delete_patch_embed(state_dict): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/benchmarking/nnUNetTrainerBenchmark_5epochs.py class nnUNetTrainerBenchmark_5epochs (line 8) | class nnUNetTrainerBenchmark_5epochs(nnUNetTrainer): method __init__ (line 9) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... method perform_actual_validation (line 18) | def perform_actual_validation(self, save_probabilities: bool = False): method save_checkpoint (line 21) | def save_checkpoint(self, filename: str) -> None: method run_training (line 25) | def run_training(self): method on_train_end (line 31) | def on_train_end(self): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/benchmarking/nnUNetTrainerBenchmark_5epochs_noDataLoading.py class nnUNetTrainerBenchmark_5epochs_noDataLoading (line 9) | class nnUNetTrainerBenchmark_5epochs_noDataLoading(nnUNetTrainerBenchmar... method __init__ (line 10) | def __init__( method get_dataloaders (line 38) | def get_dataloaders(self): method run_training (line 41) | def run_training(self): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/data_augmentation/nnUNetTrainerDA5.py class nnUNetTrainerDA5 (line 35) | class nnUNetTrainerDA5(nnUNetTrainer): method configure_rotation_dummyDA_mirroring_and_inital_patch_size (line 36) | def configure_rotation_dummyDA_mirroring_and_inital_patch_size(self): method get_training_transforms (line 94) | def get_training_transforms(patch_size: Union[np.ndarray, Tuple[int]], class nnUNetTrainerDA5ord0 (line 308) | class nnUNetTrainerDA5ord0(nnUNetTrainerDA5): method get_dataloaders (line 309) | def get_dataloaders(self): function _brightnessadditive_localgamma_transform_scale (line 357) | def _brightnessadditive_localgamma_transform_scale(x, y): function _brightness_gradient_additive_max_strength (line 361) | def _brightness_gradient_additive_max_strength(_x, _y): function _local_gamma_gamma (line 365) | def _local_gamma_gamma(): class nnUNetTrainerDA5Segord0 (line 369) | class nnUNetTrainerDA5Segord0(nnUNetTrainerDA5): method get_dataloaders (line 370) | def get_dataloaders(self): class nnUNetTrainerDA5_10epochs (line 418) | class nnUNetTrainerDA5_10epochs(nnUNetTrainerDA5): method __init__ (line 419) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/data_augmentation/nnUNetTrainerDAOrd0.py class nnUNetTrainerDAOrd0 (line 9) | class nnUNetTrainerDAOrd0(nnUNetTrainer): method get_dataloaders (line 10) | def get_dataloaders(self): class nnUNetTrainer_DASegOrd0 (line 58) | class nnUNetTrainer_DASegOrd0(nnUNetTrainer): method get_dataloaders (line 59) | def get_dataloaders(self): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/data_augmentation/nnUNetTrainerNoDA.py class nnUNetTrainerNoDA (line 9) | class nnUNetTrainerNoDA(nnUNetTrainer): method get_training_transforms (line 11) | def get_training_transforms(patch_size: Union[np.ndarray, Tuple[int]], method get_plain_dataloaders (line 27) | def get_plain_dataloaders(self, initial_patch_size: Tuple[int, ...], d... method configure_rotation_dummyDA_mirroring_and_inital_patch_size (line 33) | def configure_rotation_dummyDA_mirroring_and_inital_patch_size(self): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/data_augmentation/nnUNetTrainerNoMirroring.py class nnUNetTrainerNoMirroring (line 4) | class nnUNetTrainerNoMirroring(nnUNetTrainer): method configure_rotation_dummyDA_mirroring_and_inital_patch_size (line 5) | def configure_rotation_dummyDA_mirroring_and_inital_patch_size(self): class nnUNetTrainer_onlyMirror01 (line 13) | class nnUNetTrainer_onlyMirror01(nnUNetTrainer): method configure_rotation_dummyDA_mirroring_and_inital_patch_size (line 17) | def configure_rotation_dummyDA_mirroring_and_inital_patch_size(self): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/loss/nnUNetTrainerCELoss.py class nnUNetTrainerCELoss (line 8) | class nnUNetTrainerCELoss(nnUNetTrainer): method _build_loss (line 9) | def _build_loss(self): class nnUNetTrainerCELoss_5epochs (line 29) | class nnUNetTrainerCELoss_5epochs(nnUNetTrainerCELoss): method __init__ (line 30) | def __init__( FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/loss/nnUNetTrainerDiceLoss.py class nnUNetTrainerDiceLoss (line 11) | class nnUNetTrainerDiceLoss(nnUNetTrainer): method _build_loss (line 12) | def _build_loss(self): class nnUNetTrainerDiceCELoss_noSmooth (line 32) | class nnUNetTrainerDiceCELoss_noSmooth(nnUNetTrainer): method _build_loss (line 33) | def _build_loss(self): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/loss/nnUNetTrainerTopkLoss.py class nnUNetTrainerTopk10Loss (line 8) | class nnUNetTrainerTopk10Loss(nnUNetTrainer): method _build_loss (line 9) | def _build_loss(self): class nnUNetTrainerTopk10LossLS01 (line 30) | class nnUNetTrainerTopk10LossLS01(nnUNetTrainer): method _build_loss (line 31) | def _build_loss(self): class nnUNetTrainerDiceTopK10Loss (line 54) | class nnUNetTrainerDiceTopK10Loss(nnUNetTrainer): method _build_loss (line 55) | def _build_loss(self): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/lr_schedule/nnUNetTrainerCosAnneal.py class nnUNetTrainerCosAnneal (line 7) | class nnUNetTrainerCosAnneal(nnUNetTrainer): method configure_optimizers (line 8) | def configure_optimizers(self): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/network_architecture/nnUNetTrainerBN.py class nnUNetTrainerBN (line 9) | class nnUNetTrainerBN(nnUNetTrainer): method build_network_architecture (line 11) | def build_network_architecture(plans_manager: PlansManager, FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/network_architecture/nnUNetTrainerNoDeepSupervision.py class nnUNetTrainerNoDeepSupervision (line 5) | class nnUNetTrainerNoDeepSupervision(nnUNetTrainer): method __init__ (line 6) | def __init__( FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/optimizer/nnUNetTrainerAdam.py class nnUNetTrainerAdam (line 8) | class nnUNetTrainerAdam(nnUNetTrainer): method configure_optimizers (line 9) | def configure_optimizers(self): class nnUNetTrainerVanillaAdam (line 20) | class nnUNetTrainerVanillaAdam(nnUNetTrainer): method configure_optimizers (line 21) | def configure_optimizers(self): class nnUNetTrainerVanillaAdam1en3 (line 31) | class nnUNetTrainerVanillaAdam1en3(nnUNetTrainerVanillaAdam): method __init__ (line 32) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainerVanillaAdam3en4 (line 38) | class nnUNetTrainerVanillaAdam3en4(nnUNetTrainerVanillaAdam): method __init__ (line 40) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainerAdam1en3 (line 46) | class nnUNetTrainerAdam1en3(nnUNetTrainerAdam): method __init__ (line 47) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainerAdam3en4 (line 53) | class nnUNetTrainerAdam3en4(nnUNetTrainerAdam): method __init__ (line 55) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/optimizer/nnUNetTrainerAdan.py class nnUNetTrainerAdan (line 12) | class nnUNetTrainerAdan(nnUNetTrainer): method configure_optimizers (line 13) | def configure_optimizers(self): class nnUNetTrainerAdan1en3 (line 26) | class nnUNetTrainerAdan1en3(nnUNetTrainerAdan): method __init__ (line 27) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainerAdan3en4 (line 33) | class nnUNetTrainerAdan3en4(nnUNetTrainerAdan): method __init__ (line 35) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainerAdan1en1 (line 41) | class nnUNetTrainerAdan1en1(nnUNetTrainerAdan): method __init__ (line 43) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainerAdanCosAnneal (line 49) | class nnUNetTrainerAdanCosAnneal(nnUNetTrainerAdan): method configure_optimizers (line 55) | def configure_optimizers(self): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/sampling/nnUNetTrainer_probabilisticOversampling.py class nnUNetTrainer_probabilisticOversampling (line 11) | class nnUNetTrainer_probabilisticOversampling(nnUNetTrainer): method __init__ (line 19) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... method get_plain_dataloaders (line 27) | def get_plain_dataloaders(self, initial_patch_size: Tuple[int, ...], d... class nnUNetTrainer_probabilisticOversampling_033 (line 63) | class nnUNetTrainer_probabilisticOversampling_033(nnUNetTrainer_probabil... method __init__ (line 64) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainer_probabilisticOversampling_010 (line 70) | class nnUNetTrainer_probabilisticOversampling_010(nnUNetTrainer_probabil... method __init__ (line 71) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/training_length/nnUNetTrainer_Xepochs.py class nnUNetTrainer_5epochs (line 6) | class nnUNetTrainer_5epochs(nnUNetTrainer): method __init__ (line 7) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainer_1epoch (line 14) | class nnUNetTrainer_1epoch(nnUNetTrainer): method __init__ (line 15) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainer_10epochs (line 22) | class nnUNetTrainer_10epochs(nnUNetTrainer): method __init__ (line 23) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainer_20epochs (line 30) | class nnUNetTrainer_20epochs(nnUNetTrainer): method __init__ (line 31) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainer_50epochs (line 37) | class nnUNetTrainer_50epochs(nnUNetTrainer): method __init__ (line 38) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainer_100epochs (line 44) | class nnUNetTrainer_100epochs(nnUNetTrainer): method __init__ (line 45) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainer_250epochs (line 51) | class nnUNetTrainer_250epochs(nnUNetTrainer): method __init__ (line 52) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainer_2000epochs (line 58) | class nnUNetTrainer_2000epochs(nnUNetTrainer): method __init__ (line 59) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainer_4000epochs (line 65) | class nnUNetTrainer_4000epochs(nnUNetTrainer): method __init__ (line 66) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... class nnUNetTrainer_8000epochs (line 72) | class nnUNetTrainer_8000epochs(nnUNetTrainer): method __init__ (line 73) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/variants/training_length/nnUNetTrainer_Xepochs_NoMirroring.py class nnUNetTrainer_250epochs_NoMirroring (line 6) | class nnUNetTrainer_250epochs_NoMirroring(nnUNetTrainer): method __init__ (line 7) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... method configure_rotation_dummyDA_mirroring_and_inital_patch_size (line 12) | def configure_rotation_dummyDA_mirroring_and_inital_patch_size(self): class nnUNetTrainer_2000epochs_NoMirroring (line 20) | class nnUNetTrainer_2000epochs_NoMirroring(nnUNetTrainer): method __init__ (line 21) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... method configure_rotation_dummyDA_mirroring_and_inital_patch_size (line 26) | def configure_rotation_dummyDA_mirroring_and_inital_patch_size(self): class nnUNetTrainer_4000epochs_NoMirroring (line 34) | class nnUNetTrainer_4000epochs_NoMirroring(nnUNetTrainer): method __init__ (line 35) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... method configure_rotation_dummyDA_mirroring_and_inital_patch_size (line 40) | def configure_rotation_dummyDA_mirroring_and_inital_patch_size(self): class nnUNetTrainer_8000epochs_NoMirroring (line 48) | class nnUNetTrainer_8000epochs_NoMirroring(nnUNetTrainer): method __init__ (line 49) | def __init__(self, plans: dict, configuration: str, fold: int, dataset... method configure_rotation_dummyDA_mirroring_and_inital_patch_size (line 54) | def configure_rotation_dummyDA_mirroring_and_inital_patch_size(self): FILE: Finetune/nnUNet/nnunetv2/training/nnUNetTrainer/vit.py class Swin (line 23) | class Swin(nn.Module): method __init__ (line 24) | def __init__(self, input_channels: int, method forward (line 153) | def forward(self, x_in): method compute_conv_feature_map_size (line 170) | def compute_conv_feature_map_size(self, input_size): FILE: Finetune/nnUNet/nnunetv2/utilities/collate_outputs.py function collate_outputs (line 6) | def collate_outputs(outputs: List[dict]): FILE: Finetune/nnUNet/nnunetv2/utilities/dataset_name_id_conversion.py function find_candidate_datasets (line 21) | def find_candidate_datasets(dataset_id: int): function convert_id_to_dataset_name (line 42) | def convert_id_to_dataset_name(dataset_id: int): function convert_dataset_name_to_id (line 58) | def convert_dataset_name_to_id(dataset_name: str): function maybe_convert_to_dataset_name (line 64) | def maybe_convert_to_dataset_name(dataset_name_or_id: Union[int, str]) -... FILE: Finetune/nnUNet/nnunetv2/utilities/ddp_allgather.py function print_if_rank0 (line 20) | def print_if_rank0(*args): class AllGatherGrad (line 25) | class AllGatherGrad(torch.autograd.Function): method forward (line 28) | def forward( method backward (line 43) | def backward(ctx: Any, *grad_output: torch.Tensor) -> Tuple[torch.Tens... FILE: Finetune/nnUNet/nnunetv2/utilities/default_n_proc_DA.py function get_allowed_n_proc_DA (line 5) | def get_allowed_n_proc_DA(): FILE: Finetune/nnUNet/nnunetv2/utilities/file_path_utilities.py function convert_trainer_plans_config_to_identifier (line 11) | def convert_trainer_plans_config_to_identifier(trainer_name, plans_ident... function convert_identifier_to_trainer_plans_config (line 15) | def convert_identifier_to_trainer_plans_config(identifier: str): function get_output_folder (line 19) | def get_output_folder(dataset_name_or_id: Union[str, int], trainer_name:... function parse_dataset_trainer_plans_configuration_from_path (line 29) | def parse_dataset_trainer_plans_configuration_from_path(path: str): function get_ensemble_name (line 60) | def get_ensemble_name(model1_folder, model2_folder, folds: Tuple[int, ..... function get_ensemble_name_from_d_tr_c (line 66) | def get_ensemble_name_from_d_tr_c(dataset, tr1, p1, c1, tr2, p2, c2, fol... function convert_ensemble_folder_to_model_identifiers_and_folds (line 73) | def convert_ensemble_folder_to_model_identifiers_and_folds(ensemble_fold... function folds_tuple_to_string (line 78) | def folds_tuple_to_string(folds: Union[List[int], Tuple[int, ...]]): function folds_string_to_tuple (line 85) | def folds_string_to_tuple(folds_string: str): function check_workers_alive_and_busy (line 96) | def check_workers_alive_and_busy(export_pool: Pool, worker_list: List, r... FILE: Finetune/nnUNet/nnunetv2/utilities/find_class_by_name.py function recursive_find_python_class (line 7) | def recursive_find_python_class(folder: str, class_name: str, current_mo... FILE: Finetune/nnUNet/nnunetv2/utilities/get_network_from_plans.py function get_network_from_plans (line 9) | def get_network_from_plans(plans_manager: PlansManager, FILE: Finetune/nnUNet/nnunetv2/utilities/helpers.py function softmax_helper_dim0 (line 4) | def softmax_helper_dim0(x: torch.Tensor) -> torch.Tensor: function softmax_helper_dim1 (line 8) | def softmax_helper_dim1(x: torch.Tensor) -> torch.Tensor: function empty_cache (line 12) | def empty_cache(device: torch.device): class dummy_context (line 22) | class dummy_context(object): method __enter__ (line 23) | def __enter__(self): method __exit__ (line 26) | def __exit__(self, exc_type, exc_val, exc_tb): FILE: Finetune/nnUNet/nnunetv2/utilities/json_export.py function recursive_fix_for_json_export (line 7) | def recursive_fix_for_json_export(my_dict: dict): function fix_types_iterable (line 39) | def fix_types_iterable(iterable, output_type): FILE: Finetune/nnUNet/nnunetv2/utilities/label_handling/label_handling.py class LabelManager (line 21) | class LabelManager(object): method __init__ (line 22) | def __init__(self, label_dict: dict, regions_class_order: Union[List[i... method _sanity_check (line 51) | def _sanity_check(self, label_dict: dict): method _get_all_labels (line 62) | def _get_all_labels(self) -> List[int]: method _get_regions (line 77) | def _get_regions(self) -> Union[None, List[Union[int, Tuple[int, ...]]]]: method _determine_ignore_label (line 101) | def _determine_ignore_label(self) -> Union[None, int]: method has_regions (line 109) | def has_regions(self) -> bool: method has_ignore_label (line 113) | def has_ignore_label(self) -> bool: method all_regions (line 117) | def all_regions(self) -> Union[None, List[Union[int, Tuple[int, ...]]]]: method all_labels (line 121) | def all_labels(self) -> List[int]: method ignore_label (line 125) | def ignore_label(self) -> Union[None, int]: method apply_inference_nonlin (line 128) | def apply_inference_nonlin(self, logits: Union[np.ndarray, torch.Tenso... method convert_probabilities_to_segmentation (line 143) | def convert_probabilities_to_segmentation(self, predicted_probabilitie... method convert_logits_to_segmentation (line 177) | def convert_logits_to_segmentation(self, predicted_logits: Union[np.nd... method revert_cropping_on_probabilities (line 185) | def revert_cropping_on_probabilities(self, predicted_probabilities: Un... method filter_background (line 212) | def filter_background(classes_or_regions: Union[List[int], List[Union[... method foreground_regions (line 222) | def foreground_regions(self): method foreground_labels (line 226) | def foreground_labels(self): method num_segmentation_heads (line 230) | def num_segmentation_heads(self): function get_labelmanager_class_from_plans (line 237) | def get_labelmanager_class_from_plans(plans: dict) -> Type[LabelManager]: function convert_labelmap_to_one_hot (line 248) | def convert_labelmap_to_one_hot(segmentation: Union[np.ndarray, torch.Te... function determine_num_input_channels (line 283) | def determine_num_input_channels(plans_manager: PlansManager, FILE: Finetune/nnUNet/nnunetv2/utilities/network_initialization.py class InitWeights_He (line 4) | class InitWeights_He(object): method __init__ (line 5) | def __init__(self, neg_slope=1e-2): method __call__ (line 8) | def __call__(self, module): FILE: Finetune/nnUNet/nnunetv2/utilities/overlay_plots.py function hex_to_rgb (line 48) | def hex_to_rgb(hex: str): function generate_overlay (line 53) | def generate_overlay(input_image: np.ndarray, segmentation: np.ndarray, ... function select_slice_to_plot (line 97) | def select_slice_to_plot(image: np.ndarray, segmentation: np.ndarray) ->... function select_slice_to_plot2 (line 111) | def select_slice_to_plot2(image: np.ndarray, segmentation: np.ndarray) -... function plot_overlay (line 130) | def plot_overlay(image_file: str, segmentation_file: str, image_reader_w... function plot_overlay_preprocessed (line 152) | def plot_overlay_preprocessed(case_file: str, output_file: str, overlay_... function multiprocessing_plot_overlay (line 169) | def multiprocessing_plot_overlay(list_of_image_files, list_of_seg_files,... function multiprocessing_plot_overlay_preprocessed (line 180) | def multiprocessing_plot_overlay_preprocessed(list_of_case_files, list_o... function generate_overlays_from_raw (line 190) | def generate_overlays_from_raw(dataset_name_or_id: Union[int, str], outp... function generate_overlays_from_preprocessed (line 210) | def generate_overlays_from_preprocessed(dataset_name_or_id: Union[int, s... function entry_point_generate_overlay (line 243) | def entry_point_generate_overlay(): FILE: Finetune/nnUNet/nnunetv2/utilities/plans_handling/plans_handler.py class ConfigurationManager (line 32) | class ConfigurationManager(object): method __init__ (line 33) | def __init__(self, configuration_dict: dict): method __repr__ (line 36) | def __repr__(self): method data_identifier (line 40) | def data_identifier(self) -> str: method preprocessor_name (line 44) | def preprocessor_name(self) -> str: method preprocessor_class (line 49) | def preprocessor_class(self) -> Type[DefaultPreprocessor]: method batch_size (line 56) | def batch_size(self) -> int: method patch_size (line 60) | def patch_size(self) -> List[int]: method median_image_size_in_voxels (line 64) | def median_image_size_in_voxels(self) -> List[int]: method spacing (line 68) | def spacing(self) -> List[float]: method normalization_schemes (line 72) | def normalization_schemes(self) -> List[str]: method use_mask_for_norm (line 76) | def use_mask_for_norm(self) -> List[bool]: method UNet_class_name (line 80) | def UNet_class_name(self) -> str: method UNet_class (line 85) | def UNet_class(self) -> Type[nn.Module]: method UNet_base_num_features (line 97) | def UNet_base_num_features(self) -> int: method n_conv_per_stage_encoder (line 101) | def n_conv_per_stage_encoder(self) -> List[int]: method n_conv_per_stage_decoder (line 105) | def n_conv_per_stage_decoder(self) -> List[int]: method num_pool_per_axis (line 109) | def num_pool_per_axis(self) -> List[int]: method pool_op_kernel_sizes (line 113) | def pool_op_kernel_sizes(self) -> List[List[int]]: method conv_kernel_sizes (line 117) | def conv_kernel_sizes(self) -> List[List[int]]: method unet_max_num_features (line 121) | def unet_max_num_features(self) -> int: method resampling_fn_data (line 126) | def resampling_fn_data(self) -> Callable[ method resampling_fn_probabilities (line 139) | def resampling_fn_probabilities(self) -> Callable[ method resampling_fn_seg (line 152) | def resampling_fn_seg(self) -> Callable[ method batch_dice (line 164) | def batch_dice(self) -> bool: method next_stage_names (line 168) | def next_stage_names(self) -> Union[List[str], None]: method previous_stage_name (line 176) | def previous_stage_name(self) -> Union[str, None]: class PlansManager (line 180) | class PlansManager(object): method __init__ (line 181) | def __init__(self, plans_file_or_dict: Union[str, dict]): method __repr__ (line 194) | def __repr__(self): method _internal_resolve_configuration_inheritance (line 197) | def _internal_resolve_configuration_inheritance(self, configuration_na... method get_configuration (line 222) | def get_configuration(self, configuration_name: str): method dataset_name (line 231) | def dataset_name(self) -> str: method plans_name (line 235) | def plans_name(self) -> str: method original_median_spacing_after_transp (line 239) | def original_median_spacing_after_transp(self) -> List[float]: method original_median_shape_after_transp (line 243) | def original_median_shape_after_transp(self) -> List[float]: method image_reader_writer_class (line 248) | def image_reader_writer_class(self) -> Type[BaseReaderWriter]: method transpose_forward (line 252) | def transpose_forward(self) -> List[int]: method transpose_backward (line 256) | def transpose_backward(self) -> List[int]: method available_configurations (line 260) | def available_configurations(self) -> List[str]: method experiment_planner_class (line 265) | def experiment_planner_class(self) -> Type[ExperimentPlanner]: method experiment_planner_name (line 273) | def experiment_planner_name(self) -> str: method label_manager_class (line 278) | def label_manager_class(self) -> Type[LabelManager]: method get_label_manager (line 281) | def get_label_manager(self, dataset_json: dict, **kwargs) -> LabelMana... method foreground_intensity_properties_per_channel (line 287) | def foreground_intensity_properties_per_channel(self) -> dict: FILE: Finetune/nnUNet/nnunetv2/utilities/utils.py function get_identifiers_from_splitted_dataset_folder (line 26) | def get_identifiers_from_splitted_dataset_folder(folder: str, file_endin... function create_lists_from_splitted_dataset_folder (line 36) | def create_lists_from_splitted_dataset_folder(folder: str, file_ending: ... function get_filenames_of_train_images_and_targets (line 51) | def get_filenames_of_train_images_and_targets(raw_dataset_folder: str, d... FILE: models/voco_head.py class projection_head (line 23) | class projection_head(nn.Module): method __init__ (line 24) | def __init__(self, in_dim=768, hidden_dim=2048, out_dim=2048): method forward (line 41) | def forward(self, input): class Swin (line 56) | class Swin(nn.Module): method __init__ (line 57) | def __init__(self, args): method forward_encs (line 131) | def forward_encs(self, encs): method forward (line 140) | def forward(self, x_in): class VoCoHead (line 160) | class VoCoHead(nn.Module): method __init__ (line 161) | def __init__(self, args): method _EMA_update_encoder_teacher (line 167) | def _EMA_update_encoder_teacher(self): method forward (line 173) | def forward(self, img, crops, labels): function online_assign (line 218) | def online_assign(feats, bases): function regularization_loss (line 234) | def regularization_loss(bases): function ce_loss (line 249) | def ce_loss(labels, logits): FILE: optimizers/lr_scheduler.py class _LRSchedulerMONAI (line 23) | class _LRSchedulerMONAI(_LRScheduler): method __init__ (line 27) | def __init__(self, optimizer: Optimizer, end_lr: float, num_iter: int,... class LinearLR (line 42) | class LinearLR(_LRSchedulerMONAI): method get_lr (line 47) | def get_lr(self): class ExponentialLR (line 52) | class ExponentialLR(_LRSchedulerMONAI): method get_lr (line 57) | def get_lr(self): class WarmupCosineSchedule (line 62) | class WarmupCosineSchedule(LambdaLR): method __init__ (line 67) | def __init__( method lr_lambda (line 85) | def lr_lambda(self, step): class LinearWarmupCosineAnnealingLR (line 92) | class LinearWarmupCosineAnnealingLR(_LRScheduler): method __init__ (line 93) | def __init__( method get_lr (line 118) | def get_lr(self) -> List[float]: method _get_closed_form_lr (line 156) | def _get_closed_form_lr(self) -> List[float]: FILE: utils/data_utils.py function get_loader_1k (line 22) | def get_loader_1k(args): function random_split (line 144) | def random_split(ls): function get_loader (line 151) | def get_loader(args): function threshold (line 265) | def threshold(x): class VoCoAugmentation (line 270) | class VoCoAugmentation(): method __init__ (line 271) | def __init__(self, args, aug): method __call__ (line 275) | def __call__(self, x_in): function get_vanilla_transform (line 294) | def get_vanilla_transform(num=2, num_crops=4, roi_small=64, roi=96, max_... function get_crop_transform (line 331) | def get_crop_transform(num=4, roi_small=64, roi=96, aug=False): function get_position_label (line 377) | def get_position_label(roi=96, base_roi=96, max_roi=384, num_crops=4): FILE: utils/ops.py function patch_rand_drop (line 17) | def patch_rand_drop(args, x, x_rep=None, max_drop=0.3, max_block_sz=0.25... function rot_rand (line 46) | def rot_rand(args, x_s): function aug_rand (line 67) | def aug_rand(args, samples): function concat_image (line 78) | def concat_image(imgs): function concat_label (line 89) | def concat_label(labels): FILE: utils/utils.py function resample_3d (line 17) | def resample_3d(img, target_size): function dice (line 25) | def dice(x, y): class AverageMeter (line 34) | class AverageMeter(object): method __init__ (line 35) | def __init__(self): method reset (line 38) | def reset(self): method update (line 44) | def update(self, val, n=1): function distributed_all_gather (line 51) | def distributed_all_gather( FILE: voco_train.py function main (line 42) | def main(): function init_log (line 258) | def init_log(name, level=logging.INFO):