├── CoTr_package ├── CoTr │ ├── __init__.py │ ├── configuration.py │ ├── network_architecture │ │ ├── CNNBackbone.py │ │ ├── DeTrans │ │ │ ├── DeformableTrans.py │ │ │ ├── ops │ │ │ │ ├── functions │ │ │ │ │ └── ms_deform_attn_func.py │ │ │ │ └── modules │ │ │ │ │ ├── __init__.py │ │ │ │ │ └── ms_deform_attn.py │ │ │ └── position_encoding.py │ │ ├── ResTranUnet.py │ │ ├── __init__.py │ │ └── neural_network.py │ ├── run │ │ ├── __init__.py │ │ ├── default_configuration.py │ │ └── run_training.py │ └── training │ │ ├── __init__.py │ │ ├── model_restore.py │ │ └── network_training │ │ ├── __init__.py │ │ ├── network_trainer.py │ │ ├── nnUNetTrainer.py │ │ └── nnUNetTrainerV2_ResTrans.py └── setup.py ├── LICENSE ├── README.md ├── data └── splits_final.pkl └── nnUNet ├── LICENSE ├── documentation ├── common_problems_and_solutions.md ├── common_questions.md ├── data_format_inference.md ├── dataset_conversion.md ├── expected_epoch_times.md ├── extending_nnunet.md ├── inference_example_Prostate.md ├── setting_up_paths.md ├── training_example_Hippocampus.md └── using_nnUNet_as_baseline.md ├── nnunet ├── __init__.py ├── configuration.py ├── dataset_conversion │ ├── Task017_BeyondCranialVaultAbdominalOrganSegmentation.py │ ├── Task024_Promise2012.py │ ├── Task027_AutomaticCardiacDetectionChallenge.py │ ├── Task029_LiverTumorSegmentationChallenge.py │ ├── Task032_BraTS_2018.py │ ├── Task035_ISBI_MSLesionSegmentationChallenge.py │ ├── Task037_038_Chaos_Challenge.py │ ├── Task040_KiTS.py │ ├── Task043_BraTS_2019.py │ ├── Task055_SegTHOR.py │ ├── Task056_VerSe2019.py │ ├── Task056_Verse_normalize_orientation.py │ ├── Task058_ISBI_EM_SEG.py │ ├── Task059_EPFL_EM_MITO_SEG.py │ ├── Task061_CREMI.py │ ├── Task062_NIHPancreas.py │ ├── Task064_KiTS_labelsFixed.py │ ├── Task065_KiTS_NicksLabels.py │ ├── Task069_CovidSeg.py │ ├── Task075_Fluo_C3DH_A549_ManAndSim.py │ ├── Task076_Fluo_N3DH_SIM.py │ ├── Task082_BraTS_2020.py │ ├── Task089_Fluo-N2DH-SIM.py │ ├── Task114_heart_MNMs.py │ └── __init__.py ├── evaluation │ ├── __init__.py │ ├── add_dummy_task_with_mean_over_all_tasks.py │ ├── add_mean_dice_to_json.py │ ├── collect_results_files.py │ ├── evaluator.py │ ├── metrics.py │ ├── model_selection │ │ ├── __init__.py │ │ ├── collect_all_fold0_results_and_summarize_in_one_csv.py │ │ ├── ensemble.py │ │ ├── figure_out_what_to_submit.py │ │ ├── rank_candidates.py │ │ ├── rank_candidates_StructSeg.py │ │ ├── rank_candidates_cascade.py │ │ ├── summarize_results_in_one_json.py │ │ └── summarize_results_with_plans.py │ ├── region_based_evaluation.py │ └── surface_dice.py ├── experiment_planning │ ├── DatasetAnalyzer.py │ ├── __init__.py │ ├── alternative_experiment_planning │ │ ├── experiment_planner_baseline_3DUNet_v21_11GB.py │ │ ├── experiment_planner_baseline_3DUNet_v21_32GB.py │ │ ├── experiment_planner_baseline_3DUNet_v21_3convperstage.py │ │ ├── experiment_planner_baseline_3DUNet_v22.py │ │ ├── experiment_planner_baseline_3DUNet_v23.py │ │ ├── experiment_planner_residual_3DUNet_v21.py │ │ ├── normalization │ │ │ ├── experiment_planner_3DUNet_CT2.py │ │ │ └── experiment_planner_3DUNet_nonCT.py │ │ ├── patch_size │ │ │ ├── experiment_planner_3DUNet_isotropic_in_mm.py │ │ │ └── experiment_planner_3DUNet_isotropic_in_voxels.py │ │ ├── pooling_and_convs │ │ │ ├── experiment_planner_baseline_3DUNet_allConv3x3.py │ │ │ └── experiment_planner_baseline_3DUNet_poolBasedOnSpacing.py │ │ ├── readme.md │ │ └── target_spacing │ │ │ └── experiment_planner_baseline_3DUNet_targetSpacingForAnisoAxis.py │ ├── change_batch_size.py │ ├── common_utils.py │ ├── experiment_planner_baseline_2DUNet.py │ ├── experiment_planner_baseline_2DUNet_v21.py │ ├── experiment_planner_baseline_3DUNet.py │ ├── experiment_planner_baseline_3DUNet_v21.py │ ├── nnUNet_convert_decathlon_task.py │ ├── nnUNet_plan_and_preprocess.py │ ├── old │ │ └── old_plan_and_preprocess_task.py │ ├── summarize_plans.py │ └── utils.py ├── inference │ ├── __init__.py │ ├── change_trainer.py │ ├── ensemble_predictions.py │ ├── predict.py │ ├── predict_simple.py │ ├── pretrained_models │ │ ├── collect_pretrained_models.py │ │ └── download_pretrained_model.py │ └── segmentation_export.py ├── network_architecture │ ├── __init__.py │ ├── custom_modules │ │ ├── conv_blocks.py │ │ ├── feature_response_normalization.py │ │ ├── helperModules.py │ │ └── mish.py │ ├── generic_UNet.py │ ├── generic_UNet_DP.py │ ├── generic_modular_UNet.py │ ├── generic_modular_residual_UNet.py │ ├── initialization.py │ └── neural_network.py ├── paths.py ├── postprocessing │ ├── connected_components.py │ ├── consolidate_all_for_paper.py │ ├── consolidate_postprocessing.py │ └── consolidate_postprocessing_simple.py ├── preprocessing │ ├── __init__.py │ ├── cropping.py │ ├── preprocessing.py │ └── sanity_checks.py ├── run │ ├── __init__.py │ ├── default_configuration.py │ ├── run_training.py │ ├── run_training_DDP.py │ └── run_training_DP.py ├── training │ ├── __init__.py │ ├── cascade_stuff │ │ ├── __init__.py │ │ └── predict_next_stage.py │ ├── data_augmentation │ │ ├── __init__.py │ │ ├── custom_transforms.py │ │ ├── default_data_augmentation.py │ │ ├── downsampling.py │ │ └── pyramid_augmentations.py │ ├── dataloading │ │ ├── __init__.py │ │ └── dataset_loading.py │ ├── learning_rate │ │ └── poly_lr.py │ ├── loss_functions │ │ ├── TopK_loss.py │ │ ├── __init__.py │ │ ├── crossentropy.py │ │ ├── deep_supervision.py │ │ └── dice_loss.py │ ├── model_restore.py │ ├── network_training │ │ ├── __init__.py │ │ ├── competitions_with_custom_Trainers │ │ │ ├── BraTS2020 │ │ │ │ ├── nnUNetTrainerV2BraTSRegions.py │ │ │ │ └── nnUNetTrainerV2BraTSRegions_moreDA.py │ │ │ └── MMS │ │ │ │ └── nnUNetTrainerV2_MMS.py │ │ ├── network_trainer.py │ │ ├── nnUNetTrainer.py │ │ ├── nnUNetTrainerCascadeFullRes.py │ │ ├── nnUNetTrainerV2.py │ │ ├── nnUNetTrainerV2_CascadeFullRes.py │ │ ├── nnUNetTrainerV2_DDP.py │ │ ├── nnUNetTrainerV2_DP.py │ │ ├── nnUNetTrainerV2_fp32.py │ │ └── nnUNet_variants │ │ │ ├── __init__.py │ │ │ ├── architectural_variants │ │ │ ├── nnUNetTrainerV2_3ConvPerStage.py │ │ │ ├── nnUNetTrainerV2_3ConvPerStage_samefilters.py │ │ │ ├── nnUNetTrainerV2_BN.py │ │ │ ├── nnUNetTrainerV2_FRN.py │ │ │ ├── nnUNetTrainerV2_GN.py │ │ │ ├── nnUNetTrainerV2_GeLU.py │ │ │ ├── nnUNetTrainerV2_LReLU_slope_2en1.py │ │ │ ├── nnUNetTrainerV2_Mish.py │ │ │ ├── nnUNetTrainerV2_NoNormalization.py │ │ │ ├── nnUNetTrainerV2_NoNormalization_lr1en3.py │ │ │ ├── nnUNetTrainerV2_ReLU.py │ │ │ ├── nnUNetTrainerV2_ReLU_biasInSegOutput.py │ │ │ ├── nnUNetTrainerV2_ReLU_convReLUIN.py │ │ │ ├── nnUNetTrainerV2_ResencUNet.py │ │ │ ├── nnUNetTrainerV2_allConv3x3.py │ │ │ ├── nnUNetTrainerV2_lReLU_biasInSegOutput.py │ │ │ ├── nnUNetTrainerV2_lReLU_convlReLUIN.py │ │ │ ├── nnUNetTrainerV2_noDeepSupervision.py │ │ │ └── nnUNetTrainerV2_softDeepSupervision.py │ │ │ ├── cascade │ │ │ ├── nnUNetTrainerV2CascadeFullRes_DAVariants.py │ │ │ ├── nnUNetTrainerV2CascadeFullRes_lowerLR.py │ │ │ ├── nnUNetTrainerV2CascadeFullRes_shorter.py │ │ │ └── nnUNetTrainerV2CascadeFullRes_shorter_lowerLR.py │ │ │ ├── copies │ │ │ └── nnUNetTrainerV2_copies.py │ │ │ ├── data_augmentation │ │ │ ├── nnUNetTrainerV2_DA2.py │ │ │ ├── nnUNetTrainerV2_DA3.py │ │ │ ├── nnUNetTrainerV2_independentScalePerAxis.py │ │ │ ├── nnUNetTrainerV2_insaneDA.py │ │ │ ├── nnUNetTrainerV2_noDA.py │ │ │ └── nnUNetTrainerV2_noMirroring.py │ │ │ ├── loss_function │ │ │ ├── nnUNetTrainerV2_ForceBD.py │ │ │ ├── nnUNetTrainerV2_ForceSD.py │ │ │ ├── nnUNetTrainerV2_Loss_CE.py │ │ │ ├── nnUNetTrainerV2_Loss_CEGDL.py │ │ │ ├── nnUNetTrainerV2_Loss_Dice.py │ │ │ ├── nnUNetTrainerV2_Loss_DiceTopK10.py │ │ │ ├── nnUNetTrainerV2_Loss_Dice_lr1en3.py │ │ │ ├── nnUNetTrainerV2_Loss_Dice_squared.py │ │ │ ├── nnUNetTrainerV2_Loss_MCC.py │ │ │ ├── nnUNetTrainerV2_Loss_TopK10.py │ │ │ ├── nnUNetTrainerV2_focalLoss.py │ │ │ └── nnUNetTrainerV2_graduallyTransitionFromCEToDice.py │ │ │ ├── miscellaneous │ │ │ └── nnUNetTrainerV2_fullEvals.py │ │ │ ├── nnUNetTrainerCE.py │ │ │ ├── nnUNetTrainerNoDA.py │ │ │ ├── optimizer_and_lr │ │ │ ├── nnUNetTrainerV2_Adam.py │ │ │ ├── nnUNetTrainerV2_Adam_ReduceOnPlateau.py │ │ │ ├── nnUNetTrainerV2_Adam_lr_3en4.py │ │ │ ├── nnUNetTrainerV2_Ranger_lr1en2.py │ │ │ ├── nnUNetTrainerV2_Ranger_lr3en3.py │ │ │ ├── nnUNetTrainerV2_Ranger_lr3en4.py │ │ │ ├── nnUNetTrainerV2_SGD_ReduceOnPlateau.py │ │ │ ├── nnUNetTrainerV2_SGD_fixedSchedule.py │ │ │ ├── nnUNetTrainerV2_SGD_fixedSchedule2.py │ │ │ ├── nnUNetTrainerV2_SGD_lrs.py │ │ │ ├── nnUNetTrainerV2_cycleAtEnd.py │ │ │ ├── nnUNetTrainerV2_fp16.py │ │ │ ├── nnUNetTrainerV2_momentum09.py │ │ │ ├── nnUNetTrainerV2_momentum095.py │ │ │ ├── nnUNetTrainerV2_momentum098.py │ │ │ ├── nnUNetTrainerV2_momentum09in2D.py │ │ │ ├── nnUNetTrainerV2_reduceMomentumDuringTraining.py │ │ │ └── nnUNetTrainerV2_warmup.py │ │ │ ├── profiling │ │ │ ├── nnUNetTrainerV2_2epochs.py │ │ │ └── nnUNetTrainerV2_dummyLoad.py │ │ │ └── resampling │ │ │ └── nnUNetTrainerV2_resample33.py │ └── optimizer │ │ └── ranger.py └── utilities │ ├── __init__.py │ ├── distributed.py │ ├── file_conversions.py │ ├── file_endings.py │ ├── folder_names.py │ ├── nd_softmax.py │ ├── one_hot_encoding.py │ ├── random_stuff.py │ ├── recursive_delete_npz.py │ ├── recursive_rename_taskXX_to_taskXXX.py │ ├── sitk_stuff.py │ ├── task_name_id_conversion.py │ ├── tensor_utilities.py │ └── to_torch.py ├── readme.md ├── setup.py └── tests └── test_steps_for_sliding_window_prediction.py /CoTr_package/CoTr/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | 3 | print("This is CoTr\n") 4 | 5 | from . import * -------------------------------------------------------------------------------- /CoTr_package/CoTr/configuration.py: -------------------------------------------------------------------------------- 1 | import os 2 | 3 | default_num_threads = 8 if 'nnUNet_def_n_proc' not in os.environ else int(os.environ['nnUNet_def_n_proc']) 4 | RESAMPLING_SEPARATE_Z_ANISO_THRESHOLD = 3 # determines what threshold to use for resampling the low resolution axis 5 | # separately (with NN) -------------------------------------------------------------------------------- /CoTr_package/CoTr/network_architecture/DeTrans/ops/functions/ms_deform_attn_func.py: -------------------------------------------------------------------------------- 1 | # ------------------------------------------------------------------------ 2 | # 3D Deformable Self-attention 3 | # ------------------------------------------------------------------------ 4 | # Modified from Deformable DETR 5 | # Copyright (c) 2020 SenseTime. All Rights Reserved. 6 | # Licensed under the Apache License, Version 2.0 [see LICENSE for details] 7 | # ------------------------------------------------------------------------ 8 | 9 | from __future__ import absolute_import 10 | from __future__ import print_function 11 | from __future__ import division 12 | 13 | import torch 14 | import torch.nn.functional as F 15 | from torch.autograd import Function 16 | from torch.autograd.function import once_differentiable 17 | 18 | def ms_deform_attn_core_pytorch_3D(value, value_spatial_shapes, sampling_locations, attention_weights): 19 | N_, S_, M_, D_ = value.shape 20 | _, Lq_, M_, L_, P_, _ = sampling_locations.shape 21 | value_list = value.split([T_ * H_ * W_ for T_, H_, W_ in value_spatial_shapes], dim=1) 22 | sampling_grids = 2 * sampling_locations - 1 23 | # sampling_grids = 3 * sampling_locations - 1 24 | sampling_value_list = [] 25 | for lid_, (T_, H_, W_) in enumerate(value_spatial_shapes): 26 | value_l_ = value_list[lid_].flatten(2).transpose(1, 2).reshape(N_*M_, D_, T_, H_, W_) 27 | sampling_grid_l_ = sampling_grids[:, :, :, lid_].transpose(1, 2).flatten(0, 1)[:,None,:,:,:] 28 | sampling_value_l_ = F.grid_sample(value_l_, sampling_grid_l_.to(dtype=value_l_.dtype), mode='bilinear', padding_mode='zeros', align_corners=False)[:,:,0] 29 | sampling_value_list.append(sampling_value_l_) 30 | attention_weights = attention_weights.transpose(1, 2).reshape(N_*M_, 1, Lq_, L_*P_) 31 | output = (torch.stack(sampling_value_list, dim=-2).flatten(-2) * attention_weights).sum(-1).view(N_, M_*D_, Lq_) 32 | return output.transpose(1, 2).contiguous() -------------------------------------------------------------------------------- /CoTr_package/CoTr/network_architecture/DeTrans/ops/modules/__init__.py: -------------------------------------------------------------------------------- 1 | from .ms_deform_attn import MSDeformAttn 2 | -------------------------------------------------------------------------------- /CoTr_package/CoTr/network_architecture/DeTrans/position_encoding.py: -------------------------------------------------------------------------------- 1 | """ 2 | Positional encodings for the transformer. 3 | """ 4 | import math 5 | import torch 6 | from torch import nn 7 | from typing import Optional 8 | from torch import Tensor 9 | 10 | class PositionEmbeddingSine(nn.Module): 11 | """ 12 | This is a more standard version of the position embedding, very similar to the one 13 | used by the Attention is all you need paper, generalized to work on images. 14 | """ 15 | def __init__(self, num_pos_feats=[64, 64, 64], temperature=10000, normalize=False, scale=None): 16 | super().__init__() 17 | self.num_pos_feats = num_pos_feats 18 | self.temperature = temperature 19 | self.normalize = normalize 20 | if scale is not None and normalize is False: 21 | raise ValueError("normalize should be True if scale is passed") 22 | if scale is None: 23 | scale = 2 * math.pi 24 | self.scale = scale 25 | 26 | def forward(self, x): 27 | bs, c, d, h, w = x.shape 28 | mask = torch.zeros(bs, d, h, w, dtype=torch.bool).cuda() 29 | assert mask is not None 30 | not_mask = ~mask 31 | d_embed = not_mask.cumsum(1, dtype=torch.float32) 32 | y_embed = not_mask.cumsum(2, dtype=torch.float32) 33 | x_embed = not_mask.cumsum(3, dtype=torch.float32) 34 | if self.normalize: 35 | eps = 1e-6 36 | d_embed = (d_embed - 0.5) / (d_embed[:, -1:, :, :] + eps) * self.scale 37 | y_embed = (y_embed - 0.5) / (y_embed[:, :, -1:, :] + eps) * self.scale 38 | x_embed = (x_embed - 0.5) / (x_embed[:, :, :, -1:] + eps) * self.scale 39 | 40 | dim_tx = torch.arange(self.num_pos_feats[0], dtype=torch.float32, device=x.device) 41 | dim_tx = self.temperature ** (3 * (dim_tx // 3) / self.num_pos_feats[0]) 42 | 43 | dim_ty = torch.arange(self.num_pos_feats[1], dtype=torch.float32, device=x.device) 44 | dim_ty = self.temperature ** (3 * (dim_ty // 3) / self.num_pos_feats[1]) 45 | 46 | dim_td = torch.arange(self.num_pos_feats[2], dtype=torch.float32, device=x.device) 47 | dim_td = self.temperature ** (3 * (dim_td // 3) / self.num_pos_feats[2]) 48 | 49 | pos_x = x_embed[:, :, :, :, None] / dim_tx 50 | pos_y = y_embed[:, :, :, :, None] / dim_ty 51 | pos_d = d_embed[:, :, :, :, None] / dim_td 52 | 53 | pos_x = torch.stack((pos_x[:, :, :, :, 0::2].sin(), pos_x[:, :, :, :, 1::2].cos()), dim=5).flatten(4) 54 | pos_y = torch.stack((pos_y[:, :, :, :, 0::2].sin(), pos_y[:, :, :, :, 1::2].cos()), dim=5).flatten(4) 55 | pos_d = torch.stack((pos_d[:, :, :, :, 0::2].sin(), pos_d[:, :, :, :, 1::2].cos()), dim=5).flatten(4) 56 | 57 | pos = torch.cat((pos_d, pos_y, pos_x), dim=4).permute(0, 4, 1, 2, 3) 58 | return pos 59 | 60 | 61 | def build_position_encoding(mode, hidden_dim): 62 | N_steps = hidden_dim // 3 63 | if (hidden_dim % 3) != 0: 64 | N_steps = [N_steps, N_steps, N_steps + hidden_dim % 3] 65 | else: 66 | N_steps = [N_steps, N_steps, N_steps] 67 | 68 | if mode in ('v2', 'sine'): 69 | position_embedding = PositionEmbeddingSine(num_pos_feats=N_steps, normalize=True) 70 | else: 71 | raise ValueError(f"not supported {mode}") 72 | 73 | return position_embedding 74 | -------------------------------------------------------------------------------- /CoTr_package/CoTr/network_architecture/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /CoTr_package/CoTr/run/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /CoTr_package/CoTr/run/default_configuration.py: -------------------------------------------------------------------------------- 1 | import nnunet 2 | from nnunet.paths import network_training_output_dir, preprocessing_output_dir, default_plans_identifier 3 | from batchgenerators.utilities.file_and_folder_operations import * 4 | from nnunet.experiment_planning.summarize_plans import summarize_plans 5 | from nnunet.training.model_restore import recursive_find_python_class 6 | 7 | 8 | def get_configuration_from_output_folder(folder): 9 | # split off network_training_output_dir 10 | folder = folder[len(network_training_output_dir):] 11 | if folder.startswith("/"): 12 | folder = folder[1:] 13 | 14 | configuration, task, trainer_and_plans_identifier = folder.split("/") 15 | trainer, plans_identifier = trainer_and_plans_identifier.split("__") 16 | return configuration, task, trainer, plans_identifier 17 | 18 | 19 | def get_default_configuration(outname, network, task, network_trainer, plans_identifier=default_plans_identifier, 20 | search_in=(nnunet.__path__[0], "training", "network_training"), 21 | base_module='nnunet.training.network_training'): 22 | assert network in ['2d', '3d_lowres', '3d_fullres', '3d_cascade_fullres'], \ 23 | "network can only be one of the following: \'3d\', \'3d_lowres\', \'3d_fullres\', \'3d_cascade_fullres\'" 24 | 25 | dataset_directory = join(preprocessing_output_dir, task) 26 | 27 | if network == '2d': 28 | plans_file = join(preprocessing_output_dir, task, plans_identifier + "_plans_2D.pkl") 29 | else: 30 | plans_file = join(preprocessing_output_dir, task, plans_identifier + "_plans_3D.pkl") 31 | 32 | plans = load_pickle(plans_file) 33 | possible_stages = list(plans['plans_per_stage'].keys()) 34 | 35 | if (network == '3d_cascade_fullres' or network == "3d_lowres") and len(possible_stages) == 1: 36 | raise RuntimeError("3d_lowres/3d_cascade_fullres only applies if there is more than one stage. This task does " 37 | "not require the cascade. Run 3d_fullres instead") 38 | 39 | if network == '2d' or network == "3d_lowres": 40 | stage = 0 41 | else: 42 | stage = possible_stages[-1] 43 | 44 | trainer_class = recursive_find_python_class([join(*search_in)], network_trainer, current_module=base_module) 45 | 46 | output_folder_name = join(network_training_output_dir, network+'_'+plans_identifier, task, outname) 47 | 48 | print("###############################################") 49 | print("I am running the following nnUNet: %s" % network) 50 | print("My trainer class is: ", trainer_class) 51 | print("For that I will be using the following configuration:") 52 | summarize_plans(plans_file) 53 | print("I am using stage %d from these plans" % stage) 54 | 55 | if (network == '2d' or len(possible_stages) > 1) and not network == '3d_lowres': 56 | batch_dice = True 57 | print("I am using batch dice + CE loss") 58 | else: 59 | batch_dice = False 60 | print("I am using sample dice + CE loss") 61 | 62 | print("\nI am using data from this folder: ", join(dataset_directory, plans['data_identifier'])) 63 | print("###############################################") 64 | return plans_file, output_folder_name, dataset_directory, batch_dice, stage, trainer_class 65 | -------------------------------------------------------------------------------- /CoTr_package/CoTr/training/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /CoTr_package/CoTr/training/network_training/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /CoTr_package/setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup, find_namespace_packages 2 | 3 | setup(name='CoTr', 4 | packages=find_namespace_packages(include=["CoTr", "CoTr.*"]), 5 | version='0.0.1' 6 | ) 7 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ## CoTr: Efficient 3D Medical Image Segmentation by bridging CNN and Transformer 2 | 3 | This is the official pytorch implementation of the CoTr:
4 | 5 | **Paper: [CoTr: Efficient 3D Medical Image Segmentation 6 | by bridging CNN and Transformer](https://arxiv.org/pdf/2103.03024.pdf 7 | ).** 8 | 9 | 10 | ## Requirements 11 | CUDA 11.0
12 | Python 3.7
13 | Pytorch 1.7
14 | Torchvision 0.8.2
15 | 16 | ## Usage 17 | 18 | ### 0. Installation 19 | * Install Pytorch1.7, nnUNet and CoTr as below 20 | 21 | ``` 22 | pip install torch==1.7.1+cu110 torchvision==0.8.2+cu110 torchaudio==0.7.2 -f https://download.pytorch.org/whl/torch_stable.html 23 | 24 | cd nnUNet 25 | pip install -e . 26 | 27 | cd CoTr_package 28 | pip install -e . 29 | ``` 30 | 31 | ### 1. Data Preparation 32 | * Download [BCV dataset](https://www.synapse.org/#!Synapse:syn3193805/wiki/217789) 33 | * Preprocess the BCV dataset according to the uploaded nnUNet package. 34 | * Training and Testing ID are in `data/splits_final.pkl`. 35 | 36 | ### 2. Training 37 | cd CoTr_package/CoTr/run 38 | 39 | * Run `nohup python run_training.py -gpu='0' -outpath='CoTr' 2>&1 &` for training. 40 | 41 | ### 3. Testing 42 | * Run `nohup python run_training.py -gpu='0' -outpath='CoTr' -val --val_folder='validation_output' 2>&1 &` for validation. 43 | 44 | ### 4. Citation 45 | If this code is helpful for your study, please cite: 46 | 47 | ``` 48 | @article{xie2021cotr, 49 | title={CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation}, 50 | author={Xie, Yutong and Zhang, Jianpeng and Shen, Chunhua and Xia, Yong}, 51 | booktitle={MICCAI}, 52 | year={2021} 53 | } 54 | 55 | ``` 56 | 57 | ### 5. Acknowledgements 58 | Part of codes are reused from the [nnU-Net](https://github.com/MIC-DKFZ/nnUNet). Thanks to Fabian Isensee for the codes of nnU-Net. 59 | 60 | ### Contact 61 | Yutong Xie (yutong.xie678@gmail.com) 62 | -------------------------------------------------------------------------------- /data/splits_final.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YtongXie/CoTr/521b4cc4cc6128c0f0e08057b0b15e5c1da7cad4/data/splits_final.pkl -------------------------------------------------------------------------------- /nnUNet/documentation/data_format_inference.md: -------------------------------------------------------------------------------- 1 | # Data format for Inference 2 | 3 | The data format for inference must match the one used for the raw data (specifically, the images must be in exactly 4 | the same format as in the imagesTr folder). As before, the filenames must start with a 5 | unique identifier, followed by a 4-digit modality identifier. Here is an example for two different datasets: 6 | 7 | 1) Task005_Prostate: 8 | 9 | This task has 2 modalities, so the files in the input folder must look like this: 10 | 11 | input_folder 12 | ├── prostate_03_0000.nii.gz 13 | ├── prostate_03_0001.nii.gz 14 | ├── prostate_05_0000.nii.gz 15 | ├── prostate_05_0001.nii.gz 16 | ├── prostate_08_0000.nii.gz 17 | ├── prostate_08_0001.nii.gz 18 | ├── ... 19 | 20 | _0000 is always the T2 image and _0001 is always the ADC image (as specified by 'modality' in the dataset.json) 21 | 22 | 2) Task002_Heart: 23 | 24 | imagesTs 25 | ├── la_001_0000.nii.gz 26 | ├── la_002_0000.nii.gz 27 | ├── la_006_0000.nii.gz 28 | ├── ... 29 | 30 | Task002 only has one modality, so each case only has one _0000.nii.gz file. 31 | 32 | 33 | The segmentations in the output folder will be named INDENTIFIER.nii.gz (omitting the modality identifier). 34 | -------------------------------------------------------------------------------- /nnUNet/documentation/training_example_Hippocampus.md: -------------------------------------------------------------------------------- 1 | # Example: 3D U-Net training on the Hippocampus dataset 2 | 3 | This is a step-by-step example on how to run a 3D full resolution Training with the Hippocampus dataset from the 4 | Medical Segmentation Decathlon. 5 | 6 | 1) Install nnU-Net by following the instructions [here](../readme.md#installation). Make sure to set all relevant paths, 7 | also see [here](setting_up_paths.md). This step is necessary so that nnU-Net knows where to store raw data, 8 | preprocessed data and trained models. 9 | 2) Download the Hippocampus dataset of the Medical Segmentation Decathlon from 10 | [here](https://drive.google.com/drive/folders/1HqEgzS8BV2c7xYNrZdEAnrHk7osJJ--2). Then extract the archive to a 11 | destination of your choice. 12 | 3) Decathlon data come as 4D niftis. This is not compatible with nnU-Net (see dataset format specified 13 | [here](dataset_conversion.md)). Convert the Hippocampus dataset into the correct format with 14 | 15 | ```bash 16 | nnUNet_convert_decathlon_task -i /xxx/Task04_Hippocampus 17 | ``` 18 | 19 | Note that `Task04_Hippocampus` must be the folder that has the three 'imagesTr', 'labelsTr', 'imagesTs' subfolders! 20 | The converted dataset can be found in $nnUNet_raw_data_base/nnUNet_raw_data ($nnUNet_raw_data_base is the folder for 21 | raw data that you specified during installation) 22 | 4) You can now run nnU-Nets pipeline configuration (and the preprocessing) with the following line: 23 | ```bash 24 | nnUNet_plan_and_preprocess -t 4 25 | ``` 26 | Where 4 refers to the task ID of the Hippocampus dataset. 27 | 5) Now you can already start network training. This is how you train a 3d full resoltion U-Net on the Hippocampus dataset: 28 | ```bash 29 | nnUNet_train 3d_fullres nnUNetTrainerV2 4 0 30 | ``` 31 | nnU-Net per default requires all trainings as 5-fold cross validation. The command above will run only the training for the 32 | first fold (fold 0). 4 is the task identifier of the hippocampus dataset. Training one fold should take about 9 33 | hours on a modern GPU. 34 | 35 | This tutorial is only intended to demonstrate how easy it is to get nnU-Net running. You do not need to finish the 36 | network training - pretrained models for the hippocampus task are available (see [here](../readme.md#run-inference)). 37 | 38 | The only prerequisite for running nnU-Net on your custom dataset is to bring it into a structured, nnU-Net compatible 39 | format. nnU-Net will take care of the rest. See [here](dataset_conversion.md) for instructions on how to convert 40 | datasets into nnU-Net compatible format. 41 | -------------------------------------------------------------------------------- /nnUNet/documentation/using_nnUNet_as_baseline.md: -------------------------------------------------------------------------------- 1 | (The U-Net is the current punching bag of methods development. nnU-Net is going to be that looking forward. That is 2 | cool (great, in fact!), but it should be done correctly. Here are tips on how to benchmark against nnU-Net) 3 | 4 | This is work in progress -------------------------------------------------------------------------------- /nnUNet/nnunet/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | print("\n\nPlease cite the following paper when using nnUNet:\n\nIsensee, F., Jaeger, P.F., Kohl, S.A.A. et al. " 3 | "\"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation.\" " 4 | "Nat Methods (2020). https://doi.org/10.1038/s41592-020-01008-z\n\n") 5 | print("If you have questions or suggestions, feel free to open an issue at https://github.com/MIC-DKFZ/nnUNet\n") 6 | 7 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/configuration.py: -------------------------------------------------------------------------------- 1 | import os 2 | 3 | default_num_threads = 8 if 'nnUNet_def_n_proc' not in os.environ else int(os.environ['nnUNet_def_n_proc']) 4 | RESAMPLING_SEPARATE_Z_ANISO_THRESHOLD = 3 # determines what threshold to use for resampling the low resolution axis 5 | # separately (with NN) -------------------------------------------------------------------------------- /nnUNet/nnunet/dataset_conversion/Task024_Promise2012.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | from collections import OrderedDict 15 | import SimpleITK as sitk 16 | from batchgenerators.utilities.file_and_folder_operations import * 17 | 18 | 19 | def export_for_submission(source_dir, target_dir): 20 | """ 21 | promise wants mhd :-/ 22 | :param source_dir: 23 | :param target_dir: 24 | :return: 25 | """ 26 | files = subfiles(source_dir, suffix=".nii.gz", join=False) 27 | target_files = [join(target_dir, i[:-7] + ".mhd") for i in files] 28 | maybe_mkdir_p(target_dir) 29 | for f, t in zip(files, target_files): 30 | img = sitk.ReadImage(join(source_dir, f)) 31 | sitk.WriteImage(img, t) 32 | 33 | 34 | if __name__ == "__main__": 35 | folder = "/media/fabian/My Book/datasets/promise2012" 36 | out_folder = "/media/fabian/My Book/MedicalDecathlon/MedicalDecathlon_raw_splitted/Task024_Promise" 37 | 38 | maybe_mkdir_p(join(out_folder, "imagesTr")) 39 | maybe_mkdir_p(join(out_folder, "imagesTs")) 40 | maybe_mkdir_p(join(out_folder, "labelsTr")) 41 | # train 42 | current_dir = join(folder, "train") 43 | segmentations = subfiles(current_dir, suffix="segmentation.mhd") 44 | raw_data = [i for i in subfiles(current_dir, suffix="mhd") if not i.endswith("segmentation.mhd")] 45 | for i in raw_data: 46 | out_fname = join(out_folder, "imagesTr", i.split("/")[-1][:-4] + "_0000.nii.gz") 47 | sitk.WriteImage(sitk.ReadImage(i), out_fname) 48 | for i in segmentations: 49 | out_fname = join(out_folder, "labelsTr", i.split("/")[-1][:-17] + ".nii.gz") 50 | sitk.WriteImage(sitk.ReadImage(i), out_fname) 51 | 52 | # test 53 | current_dir = join(folder, "test") 54 | test_data = subfiles(current_dir, suffix="mhd") 55 | for i in test_data: 56 | out_fname = join(out_folder, "imagesTs", i.split("/")[-1][:-4] + "_0000.nii.gz") 57 | sitk.WriteImage(sitk.ReadImage(i), out_fname) 58 | 59 | 60 | json_dict = OrderedDict() 61 | json_dict['name'] = "PROMISE12" 62 | json_dict['description'] = "prostate" 63 | json_dict['tensorImageSize'] = "4D" 64 | json_dict['reference'] = "see challenge website" 65 | json_dict['licence'] = "see challenge website" 66 | json_dict['release'] = "0.0" 67 | json_dict['modality'] = { 68 | "0": "MRI", 69 | } 70 | json_dict['labels'] = { 71 | "0": "background", 72 | "1": "prostate" 73 | } 74 | json_dict['numTraining'] = len(raw_data) 75 | json_dict['numTest'] = len(test_data) 76 | json_dict['training'] = [{'image': "./imagesTr/%s.nii.gz" % i.split("/")[-1][:-4], "label": "./labelsTr/%s.nii.gz" % i.split("/")[-1][:-4]} for i in 77 | raw_data] 78 | json_dict['test'] = ["./imagesTs/%s.nii.gz" % i.split("/")[-1][:-4] for i in test_data] 79 | 80 | save_json(json_dict, os.path.join(out_folder, "dataset.json")) 81 | 82 | -------------------------------------------------------------------------------- /nnUNet/nnunet/dataset_conversion/Task062_NIHPancreas.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from collections import OrderedDict 17 | from nnunet.paths import nnUNet_raw_data 18 | from batchgenerators.utilities.file_and_folder_operations import * 19 | import shutil 20 | from multiprocessing import Pool 21 | import nibabel 22 | 23 | 24 | def reorient(filename): 25 | img = nibabel.load(filename) 26 | img = nibabel.as_closest_canonical(img) 27 | nibabel.save(img, filename) 28 | 29 | 30 | if __name__ == "__main__": 31 | base = "/media/fabian/DeepLearningData/Pancreas-CT" 32 | 33 | # reorient 34 | p = Pool(8) 35 | results = [] 36 | 37 | for f in subfiles(join(base, "data"), suffix=".nii.gz"): 38 | results.append(p.map_async(reorient, (f, ))) 39 | _ = [i.get() for i in results] 40 | 41 | for f in subfiles(join(base, "TCIA_pancreas_labels-02-05-2017"), suffix=".nii.gz"): 42 | results.append(p.map_async(reorient, (f, ))) 43 | _ = [i.get() for i in results] 44 | 45 | task_id = 62 46 | task_name = "NIHPancreas" 47 | 48 | foldername = "Task%03.0d_%s" % (task_id, task_name) 49 | 50 | out_base = join(nnUNet_raw_data, foldername) 51 | imagestr = join(out_base, "imagesTr") 52 | imagests = join(out_base, "imagesTs") 53 | labelstr = join(out_base, "labelsTr") 54 | maybe_mkdir_p(imagestr) 55 | maybe_mkdir_p(imagests) 56 | maybe_mkdir_p(labelstr) 57 | 58 | train_patient_names = [] 59 | test_patient_names = [] 60 | cases = list(range(1, 83)) 61 | folder_data = join(base, "data") 62 | folder_labels = join(base, "TCIA_pancreas_labels-02-05-2017") 63 | for c in cases: 64 | casename = "pancreas_%04.0d" % c 65 | shutil.copy(join(folder_data, "PANCREAS_%04.0d.nii.gz" % c), join(imagestr, casename + "_0000.nii.gz")) 66 | shutil.copy(join(folder_labels, "label%04.0d.nii.gz" % c), join(labelstr, casename + ".nii.gz")) 67 | train_patient_names.append(casename) 68 | 69 | json_dict = OrderedDict() 70 | json_dict['name'] = task_name 71 | json_dict['description'] = task_name 72 | json_dict['tensorImageSize'] = "4D" 73 | json_dict['reference'] = "see website" 74 | json_dict['licence'] = "see website" 75 | json_dict['release'] = "0.0" 76 | json_dict['modality'] = { 77 | "0": "CT", 78 | } 79 | json_dict['labels'] = { 80 | "0": "background", 81 | "1": "Pancreas", 82 | } 83 | json_dict['numTraining'] = len(train_patient_names) 84 | json_dict['numTest'] = len(test_patient_names) 85 | json_dict['training'] = [{'image': "./imagesTr/%s.nii.gz" % i.split("/")[-1], "label": "./labelsTr/%s.nii.gz" % i.split("/")[-1]} for i in 86 | train_patient_names] 87 | json_dict['test'] = ["./imagesTs/%s.nii.gz" % i.split("/")[-1] for i in test_patient_names] 88 | 89 | save_json(json_dict, os.path.join(out_base, "dataset.json")) 90 | -------------------------------------------------------------------------------- /nnUNet/nnunet/dataset_conversion/Task064_KiTS_labelsFixed.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import shutil 17 | from batchgenerators.utilities.file_and_folder_operations import * 18 | from nnunet.paths import nnUNet_raw_data 19 | 20 | 21 | if __name__ == "__main__": 22 | """ 23 | This is the KiTS dataset after Nick fixed all the labels that had errors. Downloaded on Jan 6th 2020 24 | """ 25 | 26 | base = "/media/userdisk1/Datasets/KITS2019/data" 27 | 28 | task_id = 64 29 | task_name = "KiTS_labelsFixed" 30 | 31 | foldername = "Task%03.0d_%s" % (task_id, task_name) 32 | 33 | out_base = join(nnUNet_raw_data, foldername) 34 | imagestr = join(out_base, "imagesTr") 35 | imagests = join(out_base, "imagesTs") 36 | labelstr = join(out_base, "labelsTr") 37 | maybe_mkdir_p(imagestr) 38 | maybe_mkdir_p(imagests) 39 | maybe_mkdir_p(labelstr) 40 | 41 | train_patient_names = [] 42 | test_patient_names = [] 43 | all_cases = subfolders(base, join=False) 44 | 45 | train_patients = all_cases[:210] 46 | test_patients = all_cases[210:] 47 | 48 | for p in train_patients: 49 | curr = join(base, p) 50 | label_file = join(curr, "segmentation.nii.gz") 51 | image_file = join(curr, "imaging.nii.gz") 52 | shutil.copy(image_file, join(imagestr, p + "_0000.nii.gz")) 53 | shutil.copy(label_file, join(labelstr, p + ".nii.gz")) 54 | train_patient_names.append(p) 55 | 56 | for p in test_patients: 57 | curr = join(base, p) 58 | image_file = join(curr, "imaging.nii.gz") 59 | shutil.copy(image_file, join(imagests, p + "_0000.nii.gz")) 60 | test_patient_names.append(p) 61 | 62 | json_dict = {} 63 | json_dict['name'] = "KiTS" 64 | json_dict['description'] = "kidney and kidney tumor segmentation" 65 | json_dict['tensorImageSize'] = "4D" 66 | json_dict['reference'] = "KiTS data for nnunet" 67 | json_dict['licence'] = "" 68 | json_dict['release'] = "0.0" 69 | json_dict['modality'] = { 70 | "0": "CT", 71 | } 72 | json_dict['labels'] = { 73 | "0": "background", 74 | "1": "Kidney", 75 | "2": "Tumor" 76 | } 77 | 78 | json_dict['numTraining'] = len(train_patient_names) 79 | json_dict['numTest'] = len(test_patient_names) 80 | json_dict['training'] = [{'image': "./imagesTr/%s.nii.gz" % i.split("/")[-1], "label": "./labelsTr/%s.nii.gz" % i.split("/")[-1]} for i in 81 | train_patient_names] 82 | json_dict['test'] = ["./imagesTs/%s.nii.gz" % i.split("/")[-1] for i in test_patient_names] 83 | 84 | save_json(json_dict, os.path.join(out_base, "dataset.json")) 85 | -------------------------------------------------------------------------------- /nnUNet/nnunet/dataset_conversion/Task065_KiTS_NicksLabels.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import shutil 17 | 18 | from batchgenerators.utilities.file_and_folder_operations import * 19 | from nnunet.paths import nnUNet_raw_data 20 | 21 | if __name__ == "__main__": 22 | """ 23 | Nick asked me to rerun the training with other labels (the Kidney region is defined differently). 24 | 25 | These labels operate in interpolated spacing. I don't like that but that's how it is 26 | """ 27 | 28 | base = "/media/fabian/My Book/datasets/KiTS_NicksLabels/kits19/data" 29 | labelsdir = "/media/fabian/My Book/datasets/KiTS_NicksLabels/filled_labels" 30 | 31 | task_id = 65 32 | task_name = "KiTS_NicksLabels" 33 | 34 | foldername = "Task%03.0d_%s" % (task_id, task_name) 35 | 36 | out_base = join(nnUNet_raw_data, foldername) 37 | imagestr = join(out_base, "imagesTr") 38 | imagests = join(out_base, "imagesTs") 39 | labelstr = join(out_base, "labelsTr") 40 | maybe_mkdir_p(imagestr) 41 | maybe_mkdir_p(imagests) 42 | maybe_mkdir_p(labelstr) 43 | 44 | train_patient_names = [] 45 | test_patient_names = [] 46 | all_cases = subfolders(base, join=False) 47 | 48 | train_patients = all_cases[:210] 49 | test_patients = all_cases[210:] 50 | 51 | for p in train_patients: 52 | curr = join(base, p) 53 | label_file = join(labelsdir, p + ".nii.gz") 54 | image_file = join(curr, "imaging.nii.gz") 55 | shutil.copy(image_file, join(imagestr, p + "_0000.nii.gz")) 56 | shutil.copy(label_file, join(labelstr, p + ".nii.gz")) 57 | train_patient_names.append(p) 58 | 59 | for p in test_patients: 60 | curr = join(base, p) 61 | image_file = join(curr, "imaging.nii.gz") 62 | shutil.copy(image_file, join(imagests, p + "_0000.nii.gz")) 63 | test_patient_names.append(p) 64 | 65 | json_dict = {} 66 | json_dict['name'] = "KiTS" 67 | json_dict['description'] = "kidney and kidney tumor segmentation" 68 | json_dict['tensorImageSize'] = "4D" 69 | json_dict['reference'] = "KiTS data for nnunet" 70 | json_dict['licence'] = "" 71 | json_dict['release'] = "0.0" 72 | json_dict['modality'] = { 73 | "0": "CT", 74 | } 75 | json_dict['labels'] = { 76 | "0": "background", 77 | "1": "Kidney", 78 | "2": "Tumor" 79 | } 80 | 81 | json_dict['numTraining'] = len(train_patient_names) 82 | json_dict['numTest'] = len(test_patient_names) 83 | json_dict['training'] = [{'image': "./imagesTr/%s.nii.gz" % i.split("/")[-1], "label": "./labelsTr/%s.nii.gz" % i.split("/")[-1]} for i in 84 | train_patient_names] 85 | json_dict['test'] = ["./imagesTs/%s.nii.gz" % i.split("/")[-1] for i in test_patient_names] 86 | 87 | save_json(json_dict, os.path.join(out_base, "dataset.json")) 88 | -------------------------------------------------------------------------------- /nnUNet/nnunet/dataset_conversion/Task069_CovidSeg.py: -------------------------------------------------------------------------------- 1 | import shutil 2 | 3 | from batchgenerators.utilities.file_and_folder_operations import * 4 | import SimpleITK as sitk 5 | from nnunet.paths import nnUNet_raw_data 6 | 7 | if __name__ == '__main__': 8 | #data is available at http://medicalsegmentation.com/covid19/ 9 | download_dir = '/home/fabian/Downloads' 10 | 11 | task_id = 69 12 | task_name = "CovidSeg" 13 | 14 | foldername = "Task%03.0d_%s" % (task_id, task_name) 15 | 16 | out_base = join(nnUNet_raw_data, foldername) 17 | imagestr = join(out_base, "imagesTr") 18 | imagests = join(out_base, "imagesTs") 19 | labelstr = join(out_base, "labelsTr") 20 | maybe_mkdir_p(imagestr) 21 | maybe_mkdir_p(imagests) 22 | maybe_mkdir_p(labelstr) 23 | 24 | train_patient_names = [] 25 | test_patient_names = [] 26 | 27 | # the niftis are 3d, but they are just stacks of 2d slices from different patients. So no 3d U-Net, please 28 | 29 | # the training stack has 100 slices, so we split it into 5 equally sized parts (20 slices each) for cross-validation 30 | training_data = sitk.GetArrayFromImage(sitk.ReadImage(join(download_dir, 'tr_im.nii.gz'))) 31 | training_labels = sitk.GetArrayFromImage(sitk.ReadImage(join(download_dir, 'tr_mask.nii.gz'))) 32 | 33 | for f in range(5): 34 | this_name = 'part_%d' % f 35 | data = training_data[f::5] 36 | labels = training_labels[f::5] 37 | sitk.WriteImage(sitk.GetImageFromArray(data), join(imagestr, this_name + '_0000.nii.gz')) 38 | sitk.WriteImage(sitk.GetImageFromArray(labels), join(labelstr, this_name + '.nii.gz')) 39 | train_patient_names.append(this_name) 40 | 41 | shutil.copy(join(download_dir, 'val_im.nii.gz'), join(imagests, 'val_im.nii.gz')) 42 | 43 | test_patient_names.append('val_im') 44 | 45 | json_dict = {} 46 | json_dict['name'] = task_name 47 | json_dict['description'] = "" 48 | json_dict['tensorImageSize'] = "4D" 49 | json_dict['reference'] = "" 50 | json_dict['licence'] = "" 51 | json_dict['release'] = "0.0" 52 | json_dict['modality'] = { 53 | "0": "nonct", 54 | } 55 | json_dict['labels'] = { 56 | "0": "background", 57 | "1": "stuff1", 58 | "2": "stuff2", 59 | "3": "stuff3", 60 | } 61 | 62 | json_dict['numTraining'] = len(train_patient_names) 63 | json_dict['numTest'] = len(test_patient_names) 64 | json_dict['training'] = [{'image': "./imagesTr/%s.nii.gz" % i.split("/")[-1], "label": "./labelsTr/%s.nii.gz" % i.split("/")[-1]} for i in 65 | train_patient_names] 66 | json_dict['test'] = ["./imagesTs/%s.nii.gz" % i.split("/")[-1] for i in test_patient_names] 67 | 68 | save_json(json_dict, os.path.join(out_base, "dataset.json")) 69 | -------------------------------------------------------------------------------- /nnUNet/nnunet/dataset_conversion/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | 3 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/evaluation/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/evaluation/add_dummy_task_with_mean_over_all_tasks.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | import json 16 | import numpy as np 17 | from batchgenerators.utilities.file_and_folder_operations import subfiles 18 | import os 19 | from collections import OrderedDict 20 | 21 | folder = "/home/fabian/drives/E132-Projekte/Projects/2018_MedicalDecathlon/Leaderboard" 22 | task_descriptors = ['2D final 2', 23 | '2D final, less pool, dc and topK, fold0', 24 | '2D final pseudo3d 7, fold0', 25 | '2D final, less pool, dc and ce, fold0', 26 | '3D stage0 final 2, fold0', 27 | '3D fullres final 2, fold0'] 28 | task_ids_with_no_stage0 = ["Task001_BrainTumour", "Task004_Hippocampus", "Task005_Prostate"] 29 | 30 | mean_scores = OrderedDict() 31 | for t in task_descriptors: 32 | mean_scores[t] = OrderedDict() 33 | 34 | json_files = subfiles(folder, True, None, ".json", True) 35 | json_files = [i for i in json_files if not i.split("/")[-1].startswith(".")] # stupid mac 36 | for j in json_files: 37 | with open(j, 'r') as f: 38 | res = json.load(f) 39 | task = res['task'] 40 | if task != "Task999_ALL": 41 | name = res['name'] 42 | if name in task_descriptors: 43 | if task not in list(mean_scores[name].keys()): 44 | mean_scores[name][task] = res['results']['mean']['mean'] 45 | else: 46 | raise RuntimeError("duplicate task %s for description %s" % (task, name)) 47 | 48 | for t in task_ids_with_no_stage0: 49 | mean_scores["3D stage0 final 2, fold0"][t] = mean_scores["3D fullres final 2, fold0"][t] 50 | 51 | a = set() 52 | for i in mean_scores.keys(): 53 | a = a.union(list(mean_scores[i].keys())) 54 | 55 | for i in mean_scores.keys(): 56 | try: 57 | for t in list(a): 58 | assert t in mean_scores[i].keys(), "did not find task %s for experiment %s" % (t, i) 59 | new_res = OrderedDict() 60 | new_res['name'] = i 61 | new_res['author'] = "Fabian" 62 | new_res['task'] = "Task999_ALL" 63 | new_res['results'] = OrderedDict() 64 | new_res['results']['mean'] = OrderedDict() 65 | new_res['results']['mean']['mean'] = OrderedDict() 66 | tasks = list(mean_scores[i].keys()) 67 | metrics = mean_scores[i][tasks[0]].keys() 68 | for m in metrics: 69 | foreground_values = [mean_scores[i][n][m] for n in tasks] 70 | new_res['results']['mean']["mean"][m] = np.nanmean(foreground_values) 71 | output_fname = i.replace(" ", "_") + "_globalMean.json" 72 | with open(os.path.join(folder, output_fname), 'w') as f: 73 | json.dump(new_res, f) 74 | except AssertionError: 75 | print("could not process experiment %s" % i) 76 | print("did not find task %s for experiment %s" % (t, i)) 77 | 78 | -------------------------------------------------------------------------------- /nnUNet/nnunet/evaluation/add_mean_dice_to_json.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | import json 16 | import numpy as np 17 | from batchgenerators.utilities.file_and_folder_operations import subfiles 18 | from collections import OrderedDict 19 | 20 | 21 | def foreground_mean(filename): 22 | with open(filename, 'r') as f: 23 | res = json.load(f) 24 | class_ids = np.array([int(i) for i in res['results']['mean'].keys() if (i != 'mean')]) 25 | class_ids = class_ids[class_ids != 0] 26 | class_ids = class_ids[class_ids != -1] 27 | class_ids = class_ids[class_ids != 99] 28 | 29 | tmp = res['results']['mean'].get('99') 30 | if tmp is not None: 31 | _ = res['results']['mean'].pop('99') 32 | 33 | metrics = res['results']['mean']['1'].keys() 34 | res['results']['mean']["mean"] = OrderedDict() 35 | for m in metrics: 36 | foreground_values = [res['results']['mean'][str(i)][m] for i in class_ids] 37 | res['results']['mean']["mean"][m] = np.nanmean(foreground_values) 38 | with open(filename, 'w') as f: 39 | json.dump(res, f, indent=4, sort_keys=True) 40 | 41 | 42 | def run_in_folder(folder): 43 | json_files = subfiles(folder, True, None, ".json", True) 44 | json_files = [i for i in json_files if not i.split("/")[-1].startswith(".") and not i.endswith("_globalMean.json")] # stupid mac 45 | for j in json_files: 46 | foreground_mean(j) 47 | 48 | 49 | if __name__ == "__main__": 50 | folder = "/media/fabian/Results/nnUNetOutput_final/summary_jsons" 51 | run_in_folder(folder) 52 | -------------------------------------------------------------------------------- /nnUNet/nnunet/evaluation/collect_results_files.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | import os 16 | import shutil 17 | from batchgenerators.utilities.file_and_folder_operations import subdirs, subfiles 18 | 19 | 20 | def crawl_and_copy(current_folder, out_folder, prefix="fabian_", suffix="ummary.json"): 21 | """ 22 | This script will run recursively through all subfolders of current_folder and copy all files that end with 23 | suffix with some automatically generated prefix into out_folder 24 | :param current_folder: 25 | :param out_folder: 26 | :param prefix: 27 | :return: 28 | """ 29 | s = subdirs(current_folder, join=False) 30 | f = subfiles(current_folder, join=False) 31 | f = [i for i in f if i.endswith(suffix)] 32 | if current_folder.find("fold0") != -1: 33 | for fl in f: 34 | shutil.copy(os.path.join(current_folder, fl), os.path.join(out_folder, prefix+fl)) 35 | for su in s: 36 | if prefix == "": 37 | add = su 38 | else: 39 | add = "__" + su 40 | crawl_and_copy(os.path.join(current_folder, su), out_folder, prefix=prefix+add) 41 | 42 | 43 | if __name__ == "__main__": 44 | from nnunet.paths import network_training_output_dir 45 | output_folder = "/home/fabian/PhD/results/nnUNetV2/leaderboard" 46 | crawl_and_copy(network_training_output_dir, output_folder) 47 | from nnunet.evaluation.add_mean_dice_to_json import run_in_folder 48 | run_in_folder(output_folder) 49 | -------------------------------------------------------------------------------- /nnUNet/nnunet/evaluation/model_selection/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/evaluation/surface_dice.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import numpy as np 17 | from medpy.metric.binary import __surface_distances 18 | 19 | 20 | def normalized_surface_dice(a: np.ndarray, b: np.ndarray, threshold: float, spacing: tuple = None, connectivity=1): 21 | """ 22 | This implementation differs from the official surface dice implementation! These two are not comparable!!!!! 23 | 24 | The normalized surface dice is symmetric, so it should not matter whether a or b is the reference image 25 | 26 | This implementation natively supports 2D and 3D images. Whether other dimensions are supported depends on the 27 | __surface_distances implementation in medpy 28 | 29 | :param a: image 1, must have the same shape as b 30 | :param b: image 2, must have the same shape as a 31 | :param threshold: distances below this threshold will be counted as true positives. Threshold is in mm, not voxels! 32 | (if spacing = (1, 1(, 1)) then one voxel=1mm so the threshold is effectively in voxels) 33 | must be a tuple of len dimension(a) 34 | :param spacing: how many mm is one voxel in reality? Can be left at None, we then assume an isotropic spacing of 1mm 35 | :param connectivity: see scipy.ndimage.generate_binary_structure for more information. I suggest you leave that 36 | one alone 37 | :return: 38 | """ 39 | assert all([i == j for i, j in zip(a.shape, b.shape)]), "a and b must have the same shape. a.shape= %s, " \ 40 | "b.shape= %s" % (str(a.shape), str(b.shape)) 41 | if spacing is None: 42 | spacing = tuple([1 for _ in range(len(a.shape))]) 43 | a_to_b = __surface_distances(a, b, spacing, connectivity) 44 | b_to_a = __surface_distances(b, a, spacing, connectivity) 45 | 46 | numel_a = len(a_to_b) 47 | numel_b = len(b_to_a) 48 | 49 | tp_a = np.sum(a_to_b <= threshold) / numel_a 50 | tp_b = np.sum(b_to_a <= threshold) / numel_b 51 | 52 | fp = np.sum(a_to_b > threshold) / numel_a 53 | fn = np.sum(b_to_a > threshold) / numel_b 54 | 55 | dc = (tp_a + tp_b) / (tp_a + tp_b + fp + fn + 1e-8) # 1e-8 just so that we don't get div by 0 56 | return dc 57 | 58 | -------------------------------------------------------------------------------- /nnUNet/nnunet/experiment_planning/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/experiment_planning/alternative_experiment_planning/experiment_planner_baseline_3DUNet_v21_3convperstage.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | from copy import deepcopy 16 | 17 | import numpy as np 18 | from nnunet.experiment_planning.common_utils import get_pool_and_conv_props 19 | from nnunet.experiment_planning.experiment_planner_baseline_3DUNet import ExperimentPlanner 20 | from nnunet.experiment_planning.experiment_planner_baseline_3DUNet_v21 import ExperimentPlanner3D_v21 21 | from nnunet.network_architecture.generic_UNet import Generic_UNet 22 | from nnunet.paths import * 23 | 24 | 25 | class ExperimentPlanner3D_v21_3cps(ExperimentPlanner3D_v21): 26 | """ 27 | have 3x conv-in-lrelu per resolution instead of 2 while remaining in the same memory budget 28 | 29 | This only works with 3d fullres because we use the same data as ExperimentPlanner3D_v21. Lowres would require to 30 | rerun preprocesing (different patch size = different 3d lowres target spacing) 31 | """ 32 | def __init__(self, folder_with_cropped_data, preprocessed_output_folder): 33 | super(ExperimentPlanner3D_v21_3cps, self).__init__(folder_with_cropped_data, preprocessed_output_folder) 34 | self.plans_fname = join(self.preprocessed_output_folder, 35 | "nnUNetPlansv2.1_3cps_plans_3D.pkl") 36 | self.unet_base_num_features = 32 37 | self.conv_per_stage = 3 38 | 39 | def run_preprocessing(self, num_threads): 40 | pass 41 | -------------------------------------------------------------------------------- /nnUNet/nnunet/experiment_planning/alternative_experiment_planning/experiment_planner_baseline_3DUNet_v22.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | import numpy as np 16 | from nnunet.experiment_planning.experiment_planner_baseline_3DUNet_v21 import \ 17 | ExperimentPlanner3D_v21 18 | from nnunet.paths import * 19 | 20 | 21 | class ExperimentPlanner3D_v22(ExperimentPlanner3D_v21): 22 | """ 23 | """ 24 | def __init__(self, folder_with_cropped_data, preprocessed_output_folder): 25 | super().__init__(folder_with_cropped_data, preprocessed_output_folder) 26 | self.data_identifier = "nnUNetData_plans_v2.2" 27 | self.plans_fname = join(self.preprocessed_output_folder, 28 | "nnUNetPlansv2.2_plans_3D.pkl") 29 | 30 | def get_target_spacing(self): 31 | spacings = self.dataset_properties['all_spacings'] 32 | sizes = self.dataset_properties['all_sizes'] 33 | 34 | target = np.percentile(np.vstack(spacings), self.target_spacing_percentile, 0) 35 | target_size = np.percentile(np.vstack(sizes), self.target_spacing_percentile, 0) 36 | target_size_mm = np.array(target) * np.array(target_size) 37 | # we need to identify datasets for which a different target spacing could be beneficial. These datasets have 38 | # the following properties: 39 | # - one axis which much lower resolution than the others 40 | # - the lowres axis has much less voxels than the others 41 | # - (the size in mm of the lowres axis is also reduced) 42 | worst_spacing_axis = np.argmax(target) 43 | other_axes = [i for i in range(len(target)) if i != worst_spacing_axis] 44 | other_spacings = [target[i] for i in other_axes] 45 | other_sizes = [target_size[i] for i in other_axes] 46 | 47 | has_aniso_spacing = target[worst_spacing_axis] > (self.anisotropy_threshold * max(other_spacings)) 48 | has_aniso_voxels = target_size[worst_spacing_axis] * self.anisotropy_threshold < min(other_sizes) 49 | # we don't use the last one for now 50 | #median_size_in_mm = target[target_size_mm] * RESAMPLING_SEPARATE_Z_ANISOTROPY_THRESHOLD < max(target_size_mm) 51 | 52 | if has_aniso_spacing and has_aniso_voxels: 53 | spacings_of_that_axis = np.vstack(spacings)[:, worst_spacing_axis] 54 | target_spacing_of_that_axis = np.percentile(spacings_of_that_axis, 10) 55 | # don't let the spacing of that axis get higher than self.anisotropy_thresholdxthe_other_axes 56 | target_spacing_of_that_axis = max(max(other_spacings) * self.anisotropy_threshold, target_spacing_of_that_axis) 57 | target[worst_spacing_axis] = target_spacing_of_that_axis 58 | return target 59 | 60 | -------------------------------------------------------------------------------- /nnUNet/nnunet/experiment_planning/alternative_experiment_planning/experiment_planner_baseline_3DUNet_v23.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | from nnunet.experiment_planning.experiment_planner_baseline_3DUNet_v21 import \ 16 | ExperimentPlanner3D_v21 17 | from nnunet.paths import * 18 | 19 | 20 | class ExperimentPlanner3D_v23(ExperimentPlanner3D_v21): 21 | """ 22 | """ 23 | def __init__(self, folder_with_cropped_data, preprocessed_output_folder): 24 | super(ExperimentPlanner3D_v23, self).__init__(folder_with_cropped_data, preprocessed_output_folder) 25 | self.data_identifier = "nnUNetData_plans_v2.3" 26 | self.plans_fname = join(self.preprocessed_output_folder, 27 | "nnUNetPlansv2.3_plans_3D.pkl") 28 | self.preprocessor_name = "Preprocessor3DDifferentResampling" 29 | -------------------------------------------------------------------------------- /nnUNet/nnunet/experiment_planning/alternative_experiment_planning/normalization/experiment_planner_3DUNet_CT2.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from collections import OrderedDict 17 | 18 | from nnunet.experiment_planning.experiment_planner_baseline_3DUNet import ExperimentPlanner 19 | from nnunet.paths import * 20 | 21 | 22 | class ExperimentPlannerCT2(ExperimentPlanner): 23 | """ 24 | preprocesses CT data with the "CT2" normalization. 25 | 26 | (clip range comes from training set and is the 0.5 and 99.5 percentile of intensities in foreground) 27 | CT = clip to range, then normalize with global mn and sd (computed on foreground in training set) 28 | CT2 = clip to range, normalize each case separately with its own mn and std (computed within the area that was in clip_range) 29 | """ 30 | def __init__(self, folder_with_cropped_data, preprocessed_output_folder): 31 | super(ExperimentPlannerCT2, self).__init__(folder_with_cropped_data, preprocessed_output_folder) 32 | self.data_identifier = "nnUNet_CT2" 33 | self.plans_fname = join(self.preprocessed_output_folder, "nnUNetPlans" + "CT2_plans_3D.pkl") 34 | 35 | def determine_normalization_scheme(self): 36 | schemes = OrderedDict() 37 | modalities = self.dataset_properties['modalities'] 38 | num_modalities = len(list(modalities.keys())) 39 | 40 | for i in range(num_modalities): 41 | if modalities[i] == "CT": 42 | schemes[i] = "CT2" 43 | else: 44 | schemes[i] = "nonCT" 45 | return schemes 46 | -------------------------------------------------------------------------------- /nnUNet/nnunet/experiment_planning/alternative_experiment_planning/normalization/experiment_planner_3DUNet_nonCT.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from collections import OrderedDict 17 | 18 | from nnunet.experiment_planning.experiment_planner_baseline_3DUNet import ExperimentPlanner 19 | from nnunet.paths import * 20 | 21 | 22 | class ExperimentPlannernonCT(ExperimentPlanner): 23 | """ 24 | Preprocesses all data in nonCT mode (this is what we use for MRI per default, but here it is applied to CT images 25 | as well) 26 | """ 27 | def __init__(self, folder_with_cropped_data, preprocessed_output_folder): 28 | super(ExperimentPlannernonCT, self).__init__(folder_with_cropped_data, preprocessed_output_folder) 29 | self.data_identifier = "nnUNet_nonCT" 30 | self.plans_fname = join(self.preprocessed_output_folder, "nnUNetPlans" + "nonCT_plans_3D.pkl") 31 | 32 | def determine_normalization_scheme(self): 33 | schemes = OrderedDict() 34 | modalities = self.dataset_properties['modalities'] 35 | num_modalities = len(list(modalities.keys())) 36 | 37 | for i in range(num_modalities): 38 | if modalities[i] == "CT": 39 | schemes[i] = "nonCT" 40 | else: 41 | schemes[i] = "nonCT" 42 | return schemes 43 | 44 | -------------------------------------------------------------------------------- /nnUNet/nnunet/experiment_planning/alternative_experiment_planning/readme.md: -------------------------------------------------------------------------------- 1 | These alternatives are not used in nnU-Net, but you can use them if you believe they might be better suited for you. 2 | I (Fabian) have not found them to be consistently superior. -------------------------------------------------------------------------------- /nnUNet/nnunet/experiment_planning/change_batch_size.py: -------------------------------------------------------------------------------- 1 | from batchgenerators.utilities.file_and_folder_operations import * 2 | import numpy as np 3 | 4 | if __name__ == '__main__': 5 | input_file = '/home/fabian/data/nnUNet_preprocessed/Task004_Hippocampus/nnUNetPlansv2.1_plans_3D.pkl' 6 | output_file = '/home/fabian/data/nnUNet_preprocessed/Task004_Hippocampus/nnUNetPlansv2.1_LISA_plans_3D.pkl' 7 | a = load_pickle(input_file) 8 | a['plans_per_stage'][0]['batch_size'] = int(np.floor(6 / 9 * a['plans_per_stage'][0]['batch_size'])) 9 | save_pickle(a, output_file) -------------------------------------------------------------------------------- /nnUNet/nnunet/inference/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/inference/change_trainer.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from batchgenerators.utilities.file_and_folder_operations import * 17 | 18 | 19 | def pretend_to_be_nnUNetTrainer(folder, checkpoints=("model_best.model.pkl", "model_latest.model.pkl", "model_final_checkpoint.model.pkl")): 20 | pretend_to_be_other_trainer(folder, "nnUNetTrainer", checkpoints) 21 | 22 | 23 | def pretend_to_be_other_trainer(folder, new_trainer_name, checkpoints=("model_best.model.pkl", "model_latest.model.pkl", "model_final_checkpoint.model.pkl")): 24 | folds = subdirs(folder, prefix="fold_", join=False) 25 | 26 | if isdir(join(folder, 'all')): 27 | folds.append('all') 28 | 29 | for c in checkpoints: 30 | for f in folds: 31 | checkpoint_file = join(folder, f, c) 32 | if isfile(checkpoint_file): 33 | a = load_pickle(checkpoint_file) 34 | a['name'] = new_trainer_name 35 | save_pickle(a, checkpoint_file) 36 | 37 | 38 | def main(): 39 | import argparse 40 | parser = argparse.ArgumentParser(description='Use this script to change the nnunet trainer class of a saved ' 41 | 'model. Useful for models that were trained with trainers that do ' 42 | 'not support inference (multi GPU trainers) or for trainer classes ' 43 | 'whose source code is not available. For this to work the network ' 44 | 'architecture must be identical between the original trainer ' 45 | 'class and the trainer class we are changing to. This script is ' 46 | 'experimental and only to be used by advanced users.') 47 | parser.add_argument('-i', help='Folder containing the trained model. This folder is the one containing the ' 48 | 'fold_X subfolders.') 49 | parser.add_argument('-tr', help='Name of the new trainer class') 50 | args = parser.parse_args() 51 | pretend_to_be_other_trainer(args.i, args.tr) 52 | -------------------------------------------------------------------------------- /nnUNet/nnunet/network_architecture/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/network_architecture/custom_modules/feature_response_normalization.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.utilities.tensor_utilities import mean_tensor 17 | from torch import nn 18 | import torch 19 | from torch.nn.parameter import Parameter 20 | import torch.jit 21 | 22 | 23 | class FRN3D(nn.Module): 24 | def __init__(self, num_features: int, eps=1e-6, **kwargs): 25 | super().__init__() 26 | self.eps = eps 27 | self.num_features = num_features 28 | self.weight = Parameter(torch.ones(1, num_features, 1, 1, 1), True) 29 | self.bias = Parameter(torch.zeros(1, num_features, 1, 1, 1), True) 30 | self.tau = Parameter(torch.zeros(1, num_features, 1, 1, 1), True) 31 | 32 | def forward(self, x: torch.Tensor): 33 | x = x * torch.rsqrt(mean_tensor(x * x, [2, 3, 4], keepdim=True) + self.eps) 34 | 35 | return torch.max(self.weight * x + self.bias, self.tau) 36 | 37 | 38 | if __name__ == "__main__": 39 | tmp = torch.rand((3, 32, 16, 16, 16)) 40 | 41 | frn = FRN3D(32) 42 | 43 | out = frn(tmp) 44 | -------------------------------------------------------------------------------- /nnUNet/nnunet/network_architecture/custom_modules/helperModules.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from torch import nn 17 | 18 | 19 | class Identity(nn.Module): 20 | def __init__(self, *args, **kwargs): 21 | super().__init__() 22 | 23 | def forward(self, input): 24 | return input 25 | 26 | 27 | class MyGroupNorm(nn.GroupNorm): 28 | def __init__(self, num_channels, eps=1e-5, affine=True, num_groups=8): 29 | super(MyGroupNorm, self).__init__(num_groups, num_channels, eps, affine) 30 | -------------------------------------------------------------------------------- /nnUNet/nnunet/network_architecture/custom_modules/mish.py: -------------------------------------------------------------------------------- 1 | ############ 2 | # https://github.com/lessw2020/mish/blob/master/mish.py 3 | # This code was taken from the repo above and was not created by me (Fabian)! Full credit goes to the original authors 4 | ############ 5 | 6 | import torch 7 | 8 | import torch.nn as nn 9 | import torch.nn.functional as F 10 | 11 | 12 | # Mish - "Mish: A Self Regularized Non-Monotonic Neural Activation Function" 13 | # https://arxiv.org/abs/1908.08681v1 14 | # implemented for PyTorch / FastAI by lessw2020 15 | # github: https://github.com/lessw2020/mish 16 | 17 | class Mish(nn.Module): 18 | def __init__(self): 19 | super().__init__() 20 | 21 | def forward(self, x): 22 | # inlining this saves 1 second per epoch (V100 GPU) vs having a temp x and then returning x(!) 23 | return x * (torch.tanh(F.softplus(x))) 24 | -------------------------------------------------------------------------------- /nnUNet/nnunet/network_architecture/initialization.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from torch import nn 17 | 18 | 19 | class InitWeights_He(object): 20 | def __init__(self, neg_slope=1e-2): 21 | self.neg_slope = neg_slope 22 | 23 | def __call__(self, module): 24 | if isinstance(module, nn.Conv3d) or isinstance(module, nn.Conv2d) or isinstance(module, nn.ConvTranspose2d) or isinstance(module, nn.ConvTranspose3d): 25 | module.weight = nn.init.kaiming_normal_(module.weight, a=self.neg_slope) 26 | if module.bias is not None: 27 | module.bias = nn.init.constant_(module.bias, 0) 28 | 29 | 30 | class InitWeights_XavierUniform(object): 31 | def __init__(self, gain=1): 32 | self.gain = gain 33 | 34 | def __call__(self, module): 35 | if isinstance(module, nn.Conv3d) or isinstance(module, nn.Conv2d) or isinstance(module, nn.ConvTranspose2d) or isinstance(module, nn.ConvTranspose3d): 36 | module.weight = nn.init.xavier_uniform_(module.weight, self.gain) 37 | if module.bias is not None: 38 | module.bias = nn.init.constant_(module.bias, 0) 39 | -------------------------------------------------------------------------------- /nnUNet/nnunet/paths.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | import os 16 | from batchgenerators.utilities.file_and_folder_operations import maybe_mkdir_p, join 17 | 18 | # do not modify these unless you know what you are doing 19 | my_output_identifier = "nnUNet" 20 | default_plans_identifier = "nnUNetPlansv2.1" 21 | default_data_identifier = 'nnUNet' 22 | default_trainer = "nnUNetTrainerV2" 23 | default_cascade_trainer = "nnUNetTrainerV2CascadeFullRes" 24 | 25 | """ 26 | PLEASE READ paths.md FOR INFORMATION TO HOW TO SET THIS UP 27 | """ 28 | 29 | base = os.environ['nnUNet_raw_data_base'] if "nnUNet_raw_data_base" in os.environ.keys() else None 30 | preprocessing_output_dir = os.environ['nnUNet_preprocessed'] if "nnUNet_preprocessed" in os.environ.keys() else None 31 | network_training_output_dir_base = os.path.join(os.environ['RESULTS_FOLDER']) if "RESULTS_FOLDER" in os.environ.keys() else None 32 | 33 | if base is not None: 34 | nnUNet_raw_data = join(base, "nnUNet_raw_data") 35 | nnUNet_cropped_data = join(base, "nnUNet_cropped_data") 36 | maybe_mkdir_p(nnUNet_raw_data) 37 | maybe_mkdir_p(nnUNet_cropped_data) 38 | else: 39 | print("nnUNet_raw_data_base is not defined and nnU-Net can only be used on data for which preprocessed files " 40 | "are already present on your system. nnU-Net cannot be used for experiment planning and preprocessing like " 41 | "this. If this is not intended, please read nnunet/paths.md for information on how to set this up properly.") 42 | nnUNet_cropped_data = nnUNet_raw_data = None 43 | 44 | if preprocessing_output_dir is not None: 45 | maybe_mkdir_p(preprocessing_output_dir) 46 | else: 47 | print("nnUNet_preprocessed is not defined and nnU-Net can not be used for preprocessing " 48 | "or training. If this is not intended, please read nnunet/pathy.md for information on how to set this up.") 49 | preprocessing_output_dir = None 50 | 51 | if network_training_output_dir_base is not None: 52 | network_training_output_dir = join(network_training_output_dir_base, my_output_identifier) 53 | maybe_mkdir_p(network_training_output_dir) 54 | else: 55 | print("RESULTS_FOLDER is not defined and nnU-Net cannot be used for training or " 56 | "inference. If this is not intended behavior, please read nnunet/paths.md for information on how to set this " 57 | "up") 58 | network_training_output_dir = None 59 | -------------------------------------------------------------------------------- /nnUNet/nnunet/postprocessing/consolidate_all_for_paper.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.utilities.folder_names import get_output_folder_name 17 | 18 | 19 | def get_datasets(): 20 | configurations_all = { 21 | "Task01_BrainTumour": ("3d_fullres", "2d"), 22 | "Task02_Heart": ("3d_fullres", "2d",), 23 | "Task03_Liver": ("3d_cascade_fullres", "3d_fullres", "3d_lowres", "2d"), 24 | "Task04_Hippocampus": ("3d_fullres", "2d",), 25 | "Task05_Prostate": ("3d_fullres", "2d",), 26 | "Task06_Lung": ("3d_cascade_fullres", "3d_fullres", "3d_lowres", "2d"), 27 | "Task07_Pancreas": ("3d_cascade_fullres", "3d_fullres", "3d_lowres", "2d"), 28 | "Task08_HepaticVessel": ("3d_cascade_fullres", "3d_fullres", "3d_lowres", "2d"), 29 | "Task09_Spleen": ("3d_cascade_fullres", "3d_fullres", "3d_lowres", "2d"), 30 | "Task10_Colon": ("3d_cascade_fullres", "3d_fullres", "3d_lowres", "2d"), 31 | "Task48_KiTS_clean": ("3d_cascade_fullres", "3d_lowres", "3d_fullres", "2d"), 32 | "Task27_ACDC": ("3d_fullres", "2d",), 33 | "Task24_Promise": ("3d_fullres", "2d",), 34 | "Task35_ISBILesionSegmentation": ("3d_fullres", "2d",), 35 | "Task38_CHAOS_Task_3_5_Variant2": ("3d_fullres", "2d",), 36 | "Task29_LITS": ("3d_cascade_fullres", "3d_lowres", "2d", "3d_fullres",), 37 | "Task17_AbdominalOrganSegmentation": ("3d_cascade_fullres", "3d_lowres", "2d", "3d_fullres",), 38 | "Task55_SegTHOR": ("3d_cascade_fullres", "3d_lowres", "3d_fullres", "2d",), 39 | "Task56_VerSe": ("3d_cascade_fullres", "3d_lowres", "3d_fullres", "2d",), 40 | } 41 | return configurations_all 42 | 43 | 44 | def get_commands(configurations, regular_trainer="nnUNetTrainerV2", cascade_trainer="nnUNetTrainerV2CascadeFullRes", 45 | plans="nnUNetPlansv2.1"): 46 | 47 | node_pool = ["hdf18-gpu%02.0d" % i for i in range(1, 21)] + ["hdf19-gpu%02.0d" % i for i in range(1, 8)] + ["hdf19-gpu%02.0d" % i for i in range(11, 16)] 48 | ctr = 0 49 | for task in configurations: 50 | models = configurations[task] 51 | for m in models: 52 | if m == "3d_cascade_fullres": 53 | trainer = cascade_trainer 54 | else: 55 | trainer = regular_trainer 56 | 57 | folder = get_output_folder_name(m, task, trainer, plans, overwrite_training_output_dir="/datasets/datasets_fabian/results/nnUNet") 58 | node = node_pool[ctr % len(node_pool)] 59 | print("bsub -m %s -q gputest -L /bin/bash \"source ~/.bashrc && python postprocessing/" 60 | "consolidate_postprocessing.py -f" % node, folder, "\"") 61 | ctr += 1 62 | -------------------------------------------------------------------------------- /nnUNet/nnunet/postprocessing/consolidate_postprocessing_simple.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import argparse 17 | from nnunet.postprocessing.consolidate_postprocessing import consolidate_folds 18 | from nnunet.utilities.folder_names import get_output_folder_name 19 | from nnunet.utilities.task_name_id_conversion import convert_id_to_task_name 20 | from nnunet.paths import default_cascade_trainer, default_trainer, default_plans_identifier 21 | 22 | 23 | def main(): 24 | argparser = argparse.ArgumentParser(usage="Used to determine the postprocessing for a trained model. Useful for " 25 | "when the best configuration (2d, 3d_fullres etc) as selected manually.") 26 | argparser.add_argument("-m", type=str, required=True, help="U-Net model (2d, 3d_lowres, 3d_fullres or " 27 | "3d_cascade_fullres)") 28 | argparser.add_argument("-t", type=str, required=True, help="Task name or id") 29 | argparser.add_argument("-tr", type=str, required=False, default=None, 30 | help="nnUNetTrainer class. Default: %s, unless 3d_cascade_fullres " 31 | "(then it's %s)" % (default_trainer, default_cascade_trainer)) 32 | argparser.add_argument("-pl", type=str, required=False, default=default_plans_identifier, 33 | help="Plans name, Default=%s" % default_plans_identifier) 34 | argparser.add_argument("-val", type=str, required=False, default="validation_raw", 35 | help="Validation folder name. Default: validation_raw") 36 | 37 | args = argparser.parse_args() 38 | model = args.m 39 | task = args.t 40 | trainer = args.tr 41 | plans = args.pl 42 | val = args.val 43 | 44 | if not task.startswith("Task"): 45 | task_id = int(task) 46 | task = convert_id_to_task_name(task_id) 47 | 48 | if trainer is None: 49 | if model == "3d_cascade_fullres": 50 | trainer = "nnUNetTrainerV2CascadeFullRes" 51 | else: 52 | trainer = "nnUNetTrainerV2" 53 | 54 | folder = get_output_folder_name(model, task, trainer, plans, None) 55 | 56 | consolidate_folds(folder, val) 57 | 58 | 59 | if __name__ == "__main__": 60 | main() 61 | -------------------------------------------------------------------------------- /nnUNet/nnunet/preprocessing/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/run/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/training/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/training/cascade_stuff/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/training/data_augmentation/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/training/dataloading/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/training/learning_rate/poly_lr.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | def poly_lr(epoch, max_epochs, initial_lr, exponent=0.9): 17 | return initial_lr * (1 - epoch / max_epochs)**exponent 18 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/loss_functions/TopK_loss.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | import numpy as np 16 | import torch 17 | from nnunet.training.loss_functions.crossentropy import RobustCrossEntropyLoss 18 | 19 | 20 | class TopKLoss(RobustCrossEntropyLoss): 21 | """ 22 | Network has to have NO LINEARITY! 23 | """ 24 | def __init__(self, weight=None, ignore_index=-100, k=10): 25 | self.k = k 26 | super(TopKLoss, self).__init__(weight, False, ignore_index, reduce=False) 27 | 28 | def forward(self, inp, target): 29 | target = target[:, 0].long() 30 | res = super(TopKLoss, self).forward(inp, target) 31 | num_voxels = np.prod(res.shape, dtype=np.int64) 32 | res, _ = torch.topk(res.view((-1, )), int(num_voxels * self.k / 100), sorted=False) 33 | return res.mean() 34 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/loss_functions/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/training/loss_functions/crossentropy.py: -------------------------------------------------------------------------------- 1 | from torch import nn, Tensor 2 | 3 | 4 | class RobustCrossEntropyLoss(nn.CrossEntropyLoss): 5 | """ 6 | this is just a compatibility layer because my target tensor is float and has an extra dimension 7 | """ 8 | def forward(self, input: Tensor, target: Tensor) -> Tensor: 9 | if len(target.shape) == len(input.shape): 10 | assert target.shape[1] == 1 11 | target = target[:, 0] 12 | return super().forward(input, target.long()) -------------------------------------------------------------------------------- /nnUNet/nnunet/training/loss_functions/deep_supervision.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from torch import nn 17 | 18 | 19 | class MultipleOutputLoss2(nn.Module): 20 | def __init__(self, loss, weight_factors=None): 21 | """ 22 | use this if you have several outputs and ground truth (both list of same len) and the loss should be computed 23 | between them (x[0] and y[0], x[1] and y[1] etc) 24 | :param loss: 25 | :param weight_factors: 26 | """ 27 | super(MultipleOutputLoss2, self).__init__() 28 | self.weight_factors = weight_factors 29 | self.loss = loss 30 | 31 | def forward(self, x, y): 32 | assert isinstance(x, (tuple, list)), "x must be either tuple or list" 33 | assert isinstance(y, (tuple, list)), "y must be either tuple or list" 34 | if self.weight_factors is None: 35 | weights = [1] * len(x) 36 | else: 37 | weights = self.weight_factors 38 | 39 | l = weights[0] * self.loss(x[0], y[0]) 40 | for i in range(1, len(x)): 41 | if weights[i] != 0: 42 | l += weights[i] * self.loss(x[i], y[i]) 43 | return l 44 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/competitions_with_custom_Trainers/MMS/nnUNetTrainerV2_MMS.py: -------------------------------------------------------------------------------- 1 | import torch 2 | from nnunet.network_architecture.generic_UNet import Generic_UNet 3 | from nnunet.network_architecture.initialization import InitWeights_He 4 | from nnunet.training.network_training.nnUNet_variants.data_augmentation.nnUNetTrainerV2_insaneDA import \ 5 | nnUNetTrainerV2_insaneDA 6 | from nnunet.utilities.nd_softmax import softmax_helper 7 | from torch import nn 8 | 9 | 10 | class nnUNetTrainerV2_MMS(nnUNetTrainerV2_insaneDA): 11 | def setup_DA_params(self): 12 | super().setup_DA_params() 13 | self.data_aug_params["p_rot"] = 0.7 14 | self.data_aug_params["p_eldef"] = 0.1 15 | self.data_aug_params["p_scale"] = 0.3 16 | 17 | self.data_aug_params["independent_scale_factor_for_each_axis"] = True 18 | self.data_aug_params["p_independent_scale_per_axis"] = 0.3 19 | 20 | self.data_aug_params["do_additive_brightness"] = True 21 | self.data_aug_params["additive_brightness_mu"] = 0 22 | self.data_aug_params["additive_brightness_sigma"] = 0.2 23 | self.data_aug_params["additive_brightness_p_per_sample"] = 0.3 24 | self.data_aug_params["additive_brightness_p_per_channel"] = 1 25 | 26 | self.data_aug_params["elastic_deform_alpha"] = (0., 300.) 27 | self.data_aug_params["elastic_deform_sigma"] = (9., 15.) 28 | 29 | self.data_aug_params['gamma_range'] = (0.5, 1.6) 30 | 31 | def initialize_network(self): 32 | if self.threeD: 33 | conv_op = nn.Conv3d 34 | dropout_op = nn.Dropout3d 35 | norm_op = nn.BatchNorm3d 36 | 37 | else: 38 | conv_op = nn.Conv2d 39 | dropout_op = nn.Dropout2d 40 | norm_op = nn.BatchNorm2d 41 | 42 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 43 | dropout_op_kwargs = {'p': 0, 'inplace': True} 44 | net_nonlin = nn.LeakyReLU 45 | net_nonlin_kwargs = {'negative_slope': 1e-2, 'inplace': True} 46 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 47 | len(self.net_num_pool_op_kernel_sizes), 48 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, 49 | dropout_op_kwargs, 50 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(1e-2), 51 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True) 52 | if torch.cuda.is_available(): 53 | self.network.cuda() 54 | self.network.inference_apply_nonlin = softmax_helper 55 | 56 | """def run_training(self): 57 | from batchviewer import view_batch 58 | a = next(self.tr_gen) 59 | view_batch(a['data']) 60 | import IPython;IPython.embed()""" 61 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNetTrainerV2_fp32.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | 18 | 19 | class nnUNetTrainerV2_fp32(nnUNetTrainerV2): 20 | """ 21 | Info for Fabian: same as internal nnUNetTrainerV2_2 22 | """ 23 | 24 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 25 | unpack_data=True, deterministic=True, fp16=False): 26 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 27 | deterministic, False) 28 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_3ConvPerStage.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | from torch import nn 20 | 21 | 22 | class nnUNetTrainerV2_3ConvPerStage(nnUNetTrainerV2): 23 | def initialize_network(self): 24 | self.base_num_features = 24 # otherwise we run out of VRAM 25 | if self.threeD: 26 | conv_op = nn.Conv3d 27 | dropout_op = nn.Dropout3d 28 | norm_op = nn.InstanceNorm3d 29 | 30 | else: 31 | conv_op = nn.Conv2d 32 | dropout_op = nn.Dropout2d 33 | norm_op = nn.InstanceNorm2d 34 | 35 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 36 | dropout_op_kwargs = {'p': 0, 'inplace': True} 37 | net_nonlin = nn.LeakyReLU 38 | net_nonlin_kwargs = {'negative_slope': 1e-2, 'inplace': True} 39 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 40 | len(self.net_num_pool_op_kernel_sizes), 41 | 3, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 42 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(1e-2), 43 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True) 44 | if torch.cuda.is_available(): 45 | self.network.cuda() 46 | self.network.inference_apply_nonlin = softmax_helper 47 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_3ConvPerStage_samefilters.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | from torch import nn 20 | 21 | 22 | class nnUNetTrainerV2_3ConvPerStageSameFilters(nnUNetTrainerV2): 23 | def initialize_network(self): 24 | if self.threeD: 25 | conv_op = nn.Conv3d 26 | dropout_op = nn.Dropout3d 27 | norm_op = nn.InstanceNorm3d 28 | 29 | else: 30 | conv_op = nn.Conv2d 31 | dropout_op = nn.Dropout2d 32 | norm_op = nn.InstanceNorm2d 33 | 34 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 35 | dropout_op_kwargs = {'p': 0, 'inplace': True} 36 | net_nonlin = nn.LeakyReLU 37 | net_nonlin_kwargs = {'negative_slope': 1e-2, 'inplace': True} 38 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 39 | len(self.net_num_pool_op_kernel_sizes), 40 | 3, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 41 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(1e-2), 42 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True) 43 | if torch.cuda.is_available(): 44 | self.network.cuda() 45 | self.network.inference_apply_nonlin = softmax_helper 46 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_BN.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | from torch import nn 20 | 21 | 22 | class nnUNetTrainerV2_BN(nnUNetTrainerV2): 23 | def initialize_network(self): 24 | """ 25 | changed deep supervision to False 26 | :return: 27 | """ 28 | if self.threeD: 29 | conv_op = nn.Conv3d 30 | dropout_op = nn.Dropout3d 31 | norm_op = nn.BatchNorm3d 32 | 33 | else: 34 | conv_op = nn.Conv2d 35 | dropout_op = nn.Dropout2d 36 | norm_op = nn.BatchNorm2d 37 | 38 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 39 | dropout_op_kwargs = {'p': 0, 'inplace': True} 40 | net_nonlin = nn.LeakyReLU 41 | net_nonlin_kwargs = {'negative_slope': 1e-2, 'inplace': True} 42 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 43 | len(self.net_num_pool_op_kernel_sizes), 44 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 45 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(1e-2), 46 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True) 47 | if torch.cuda.is_available(): 48 | self.network.cuda() 49 | self.network.inference_apply_nonlin = softmax_helper 50 | 51 | 52 | nnUNetTrainerV2_BN_copy1 = nnUNetTrainerV2_BN 53 | nnUNetTrainerV2_BN_copy2 = nnUNetTrainerV2_BN 54 | nnUNetTrainerV2_BN_copy3 = nnUNetTrainerV2_BN 55 | nnUNetTrainerV2_BN_copy4 = nnUNetTrainerV2_BN 56 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_FRN.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.network_architecture.custom_modules.feature_response_normalization import FRN3D 17 | from nnunet.network_architecture.generic_UNet import Generic_UNet 18 | from nnunet.network_architecture.initialization import InitWeights_He 19 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 20 | from nnunet.utilities.nd_softmax import softmax_helper 21 | from torch import nn 22 | from nnunet.network_architecture.custom_modules.helperModules import Identity 23 | import torch 24 | 25 | 26 | class nnUNetTrainerV2_FRN(nnUNetTrainerV2): 27 | def initialize_network(self): 28 | """ 29 | changed deep supervision to False 30 | :return: 31 | """ 32 | if self.threeD: 33 | conv_op = nn.Conv3d 34 | dropout_op = nn.Dropout3d 35 | norm_op = FRN3D 36 | 37 | else: 38 | conv_op = nn.Conv2d 39 | dropout_op = nn.Dropout2d 40 | raise NotImplementedError 41 | norm_op = nn.BatchNorm2d 42 | 43 | norm_op_kwargs = {'eps': 1e-6} 44 | dropout_op_kwargs = {'p': 0, 'inplace': True} 45 | net_nonlin = Identity 46 | net_nonlin_kwargs = {} 47 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 48 | len(self.net_num_pool_op_kernel_sizes), 49 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 50 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(1e-2), 51 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True) 52 | if torch.cuda.is_available(): 53 | self.network.cuda() 54 | self.network.inference_apply_nonlin = softmax_helper 55 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_GN.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.network_architecture.custom_modules.helperModules import MyGroupNorm 19 | from nnunet.utilities.nd_softmax import softmax_helper 20 | from torch import nn 21 | 22 | 23 | class nnUNetTrainerV2_GN(nnUNetTrainerV2): 24 | def initialize_network(self): 25 | """ 26 | changed deep supervision to False 27 | :return: 28 | """ 29 | if self.threeD: 30 | conv_op = nn.Conv3d 31 | dropout_op = nn.Dropout3d 32 | norm_op = MyGroupNorm 33 | 34 | else: 35 | conv_op = nn.Conv2d 36 | dropout_op = nn.Dropout2d 37 | norm_op = MyGroupNorm 38 | 39 | norm_op_kwargs = {'eps': 1e-5, 'affine': True, 'num_groups': 8} 40 | dropout_op_kwargs = {'p': 0, 'inplace': True} 41 | net_nonlin = nn.LeakyReLU 42 | net_nonlin_kwargs = {'negative_slope': 1e-2, 'inplace': True} 43 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 44 | len(self.net_num_pool_op_kernel_sizes), 45 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 46 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(1e-2), 47 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True) 48 | if torch.cuda.is_available(): 49 | self.network.cuda() 50 | self.network.inference_apply_nonlin = softmax_helper 51 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_GeLU.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | 18 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 19 | from nnunet.utilities.nd_softmax import softmax_helper 20 | from torch import nn 21 | 22 | try: 23 | from torch.nn.functional import gelu 24 | except ImportError: 25 | gelu = None 26 | 27 | 28 | class GeLU(nn.Module): 29 | def __init__(self): 30 | super().__init__() 31 | if gelu is None: 32 | raise ImportError('You need to have at least torch==1.7.0 to use GeLUs') 33 | 34 | def forward(self, x): 35 | return gelu(x) 36 | 37 | 38 | class nnUNetTrainerV2_GeLU(nnUNetTrainerV2): 39 | def initialize_network(self): 40 | """ 41 | - momentum 0.99 42 | - SGD instead of Adam 43 | - self.lr_scheduler = None because we do poly_lr 44 | - deep supervision = True 45 | - ReLU 46 | - i am sure I forgot something here 47 | 48 | Known issue: forgot to set neg_slope=0 in InitWeights_He; should not make a difference though 49 | :return: 50 | """ 51 | if self.threeD: 52 | conv_op = nn.Conv3d 53 | dropout_op = nn.Dropout3d 54 | norm_op = nn.InstanceNorm3d 55 | 56 | else: 57 | conv_op = nn.Conv2d 58 | dropout_op = nn.Dropout2d 59 | norm_op = nn.InstanceNorm2d 60 | 61 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 62 | dropout_op_kwargs = {'p': 0, 'inplace': True} 63 | net_nonlin = GeLU 64 | net_nonlin_kwargs = {} 65 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 66 | len(self.net_num_pool_op_kernel_sizes), 67 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 68 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(), 69 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True) 70 | if torch.cuda.is_available(): 71 | self.network.cuda() 72 | self.network.inference_apply_nonlin = softmax_helper 73 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_LReLU_slope_2en1.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | from torch import nn 20 | 21 | 22 | class nnUNetTrainerV2_LReLU_slope_2en1(nnUNetTrainerV2): 23 | def initialize_network(self): 24 | if self.threeD: 25 | conv_op = nn.Conv3d 26 | dropout_op = nn.Dropout3d 27 | norm_op = nn.InstanceNorm3d 28 | 29 | else: 30 | conv_op = nn.Conv2d 31 | dropout_op = nn.Dropout2d 32 | norm_op = nn.InstanceNorm2d 33 | 34 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 35 | dropout_op_kwargs = {'p': 0, 'inplace': True} 36 | net_nonlin = nn.LeakyReLU 37 | net_nonlin_kwargs = {'inplace': True, 'negative_slope': 2e-1} 38 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 39 | len(self.net_num_pool_op_kernel_sizes), 40 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 41 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(0), 42 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True) 43 | if torch.cuda.is_available(): 44 | self.network.cuda() 45 | self.network.inference_apply_nonlin = softmax_helper 46 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_Mish.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | from torch import nn 20 | from nnunet.network_architecture.custom_modules.mish import Mish 21 | 22 | 23 | class nnUNetTrainerV2_Mish(nnUNetTrainerV2): 24 | def initialize_network(self): 25 | if self.threeD: 26 | conv_op = nn.Conv3d 27 | dropout_op = nn.Dropout3d 28 | norm_op = nn.InstanceNorm3d 29 | 30 | else: 31 | conv_op = nn.Conv2d 32 | dropout_op = nn.Dropout2d 33 | norm_op = nn.InstanceNorm2d 34 | 35 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 36 | dropout_op_kwargs = {'p': 0, 'inplace': True} 37 | net_nonlin = Mish 38 | net_nonlin_kwargs = {} 39 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 40 | len(self.net_num_pool_op_kernel_sizes), 41 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 42 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(0), 43 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True) 44 | if torch.cuda.is_available(): 45 | self.network.cuda() 46 | self.network.inference_apply_nonlin = softmax_helper 47 | 48 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_NoNormalization.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.network_architecture.custom_modules.helperModules import Identity 19 | from nnunet.utilities.nd_softmax import softmax_helper 20 | from torch import nn 21 | 22 | 23 | class nnUNetTrainerV2_NoNormalization(nnUNetTrainerV2): 24 | def initialize_network(self): 25 | if self.threeD: 26 | conv_op = nn.Conv3d 27 | dropout_op = nn.Dropout3d 28 | norm_op = Identity 29 | 30 | else: 31 | conv_op = nn.Conv2d 32 | dropout_op = nn.Dropout2d 33 | norm_op = Identity 34 | 35 | norm_op_kwargs = {} 36 | dropout_op_kwargs = {'p': 0, 'inplace': True} 37 | net_nonlin = nn.LeakyReLU 38 | net_nonlin_kwargs = {'negative_slope': 1e-2, 'inplace': True} 39 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 40 | len(self.net_num_pool_op_kernel_sizes), 41 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 42 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(1e-2), 43 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True) 44 | if torch.cuda.is_available(): 45 | self.network.cuda() 46 | self.network.inference_apply_nonlin = softmax_helper 47 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_NoNormalization_lr1en3.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNet_variants.architectural_variants.nnUNetTrainerV2_NoNormalization import \ 17 | nnUNetTrainerV2_NoNormalization 18 | 19 | 20 | class nnUNetTrainerV2_NoNormalization_lr1en3(nnUNetTrainerV2_NoNormalization): 21 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 22 | unpack_data=True, deterministic=True, fp16=False): 23 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 24 | deterministic, fp16) 25 | self.initial_lr = 1e-3 26 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_ReLU.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | from torch import nn 20 | 21 | 22 | class nnUNetTrainerV2_ReLU(nnUNetTrainerV2): 23 | def initialize_network(self): 24 | if self.threeD: 25 | conv_op = nn.Conv3d 26 | dropout_op = nn.Dropout3d 27 | norm_op = nn.InstanceNorm3d 28 | 29 | else: 30 | conv_op = nn.Conv2d 31 | dropout_op = nn.Dropout2d 32 | norm_op = nn.InstanceNorm2d 33 | 34 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 35 | dropout_op_kwargs = {'p': 0, 'inplace': True} 36 | net_nonlin = nn.ReLU 37 | net_nonlin_kwargs = {'inplace': True} 38 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 39 | len(self.net_num_pool_op_kernel_sizes), 40 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 41 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(0), 42 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True) 43 | if torch.cuda.is_available(): 44 | self.network.cuda() 45 | self.network.inference_apply_nonlin = softmax_helper 46 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_ReLU_biasInSegOutput.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | from torch import nn 20 | 21 | 22 | class nnUNetTrainerV2_ReLU_biasInSegOutput(nnUNetTrainerV2): 23 | def initialize_network(self): 24 | if self.threeD: 25 | conv_op = nn.Conv3d 26 | dropout_op = nn.Dropout3d 27 | norm_op = nn.InstanceNorm3d 28 | 29 | else: 30 | conv_op = nn.Conv2d 31 | dropout_op = nn.Dropout2d 32 | norm_op = nn.InstanceNorm2d 33 | 34 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 35 | dropout_op_kwargs = {'p': 0, 'inplace': True} 36 | net_nonlin = nn.ReLU 37 | net_nonlin_kwargs = {'inplace': True} 38 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 39 | len(self.net_num_pool_op_kernel_sizes), 40 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 41 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(0), 42 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True, 43 | seg_output_use_bias=True) 44 | if torch.cuda.is_available(): 45 | self.network.cuda() 46 | self.network.inference_apply_nonlin = softmax_helper 47 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_ReLU_convReLUIN.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet, ConvDropoutNonlinNorm 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | from torch import nn 20 | 21 | 22 | class nnUNetTrainerV2_ReLU_convReLUIN(nnUNetTrainerV2): 23 | def initialize_network(self): 24 | if self.threeD: 25 | conv_op = nn.Conv3d 26 | dropout_op = nn.Dropout3d 27 | norm_op = nn.InstanceNorm3d 28 | 29 | else: 30 | conv_op = nn.Conv2d 31 | dropout_op = nn.Dropout2d 32 | norm_op = nn.InstanceNorm2d 33 | 34 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 35 | dropout_op_kwargs = {'p': 0, 'inplace': True} 36 | net_nonlin = nn.ReLU 37 | net_nonlin_kwargs = {'inplace': True} 38 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 39 | len(self.net_num_pool_op_kernel_sizes), 40 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 41 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(0), 42 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True, 43 | basic_block=ConvDropoutNonlinNorm) 44 | if torch.cuda.is_available(): 45 | self.network.cuda() 46 | self.network.inference_apply_nonlin = softmax_helper 47 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_allConv3x3.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | from torch import nn 20 | 21 | 22 | class nnUNetTrainerV2_allConv3x3(nnUNetTrainerV2): 23 | def initialize_network(self): 24 | """ 25 | - momentum 0.99 26 | - SGD instead of Adam 27 | - self.lr_scheduler = None because we do poly_lr 28 | - deep supervision = True 29 | - i am sure I forgot something here 30 | 31 | Known issue: forgot to set neg_slope=0 in InitWeights_He; should not make a difference though 32 | :return: 33 | """ 34 | if self.threeD: 35 | conv_op = nn.Conv3d 36 | dropout_op = nn.Dropout3d 37 | norm_op = nn.InstanceNorm3d 38 | 39 | else: 40 | conv_op = nn.Conv2d 41 | dropout_op = nn.Dropout2d 42 | norm_op = nn.InstanceNorm2d 43 | 44 | for s in range(len(self.net_conv_kernel_sizes)): 45 | for i in range(len(self.net_conv_kernel_sizes[s])): 46 | self.net_conv_kernel_sizes[s][i] = 3 47 | 48 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 49 | dropout_op_kwargs = {'p': 0, 'inplace': True} 50 | net_nonlin = nn.LeakyReLU 51 | net_nonlin_kwargs = {'negative_slope': 1e-2, 'inplace': True} 52 | 53 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 54 | len(self.net_num_pool_op_kernel_sizes), 55 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 56 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(1e-2), 57 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True) 58 | if torch.cuda.is_available(): 59 | self.network.cuda() 60 | self.network.inference_apply_nonlin = softmax_helper 61 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_lReLU_biasInSegOutput.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | from torch import nn 20 | 21 | 22 | class nnUNetTrainerV2_lReLU_biasInSegOutput(nnUNetTrainerV2): 23 | def initialize_network(self): 24 | if self.threeD: 25 | conv_op = nn.Conv3d 26 | dropout_op = nn.Dropout3d 27 | norm_op = nn.InstanceNorm3d 28 | 29 | else: 30 | conv_op = nn.Conv2d 31 | dropout_op = nn.Dropout2d 32 | norm_op = nn.InstanceNorm2d 33 | 34 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 35 | dropout_op_kwargs = {'p': 0, 'inplace': True} 36 | net_nonlin = nn.LeakyReLU 37 | net_nonlin_kwargs = {'negative_slope': 1e-2, 'inplace': True} 38 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 39 | len(self.net_num_pool_op_kernel_sizes), 40 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 41 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(0), 42 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True, 43 | seg_output_use_bias=True) 44 | if torch.cuda.is_available(): 45 | self.network.cuda() 46 | self.network.inference_apply_nonlin = softmax_helper 47 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/architectural_variants/nnUNetTrainerV2_lReLU_convlReLUIN.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import torch 15 | from nnunet.network_architecture.generic_UNet import Generic_UNet, ConvDropoutNonlinNorm 16 | from nnunet.network_architecture.initialization import InitWeights_He 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | from torch import nn 20 | 21 | 22 | class nnUNetTrainerV2_lReLU_convReLUIN(nnUNetTrainerV2): 23 | def initialize_network(self): 24 | if self.threeD: 25 | conv_op = nn.Conv3d 26 | dropout_op = nn.Dropout3d 27 | norm_op = nn.InstanceNorm3d 28 | 29 | else: 30 | conv_op = nn.Conv2d 31 | dropout_op = nn.Dropout2d 32 | norm_op = nn.InstanceNorm2d 33 | 34 | norm_op_kwargs = {'eps': 1e-5, 'affine': True} 35 | dropout_op_kwargs = {'p': 0, 'inplace': True} 36 | net_nonlin = nn.LeakyReLU 37 | net_nonlin_kwargs = {'inplace': True, 'negative_slope': 1e-2} 38 | self.network = Generic_UNet(self.num_input_channels, self.base_num_features, self.num_classes, 39 | len(self.net_num_pool_op_kernel_sizes), 40 | self.conv_per_stage, 2, conv_op, norm_op, norm_op_kwargs, dropout_op, dropout_op_kwargs, 41 | net_nonlin, net_nonlin_kwargs, True, False, lambda x: x, InitWeights_He(1e-2), 42 | self.net_num_pool_op_kernel_sizes, self.net_conv_kernel_sizes, False, True, True, 43 | basic_block=ConvDropoutNonlinNorm) 44 | if torch.cuda.is_available(): 45 | self.network.cuda() 46 | self.network.inference_apply_nonlin = softmax_helper 47 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/cascade/nnUNetTrainerV2CascadeFullRes_lowerLR.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2_CascadeFullRes import nnUNetTrainerV2CascadeFullRes 17 | 18 | 19 | class nnUNetTrainerV2CascadeFullRes_lowerLR(nnUNetTrainerV2CascadeFullRes): 20 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 21 | unpack_data=True, deterministic=True, previous_trainer="nnUNetTrainerV2", fp16=False): 22 | super().__init__(plans_file, fold, output_folder, dataset_directory, 23 | batch_dice, stage, unpack_data, deterministic, 24 | previous_trainer, fp16) 25 | self.initial_lr = 1e-3 26 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/cascade/nnUNetTrainerV2CascadeFullRes_shorter.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2_CascadeFullRes import nnUNetTrainerV2CascadeFullRes 17 | 18 | 19 | class nnUNetTrainerV2CascadeFullRes_shorter(nnUNetTrainerV2CascadeFullRes): 20 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 21 | unpack_data=True, deterministic=True, previous_trainer="nnUNetTrainerV2", fp16=False): 22 | super().__init__(plans_file, fold, output_folder, dataset_directory, 23 | batch_dice, stage, unpack_data, deterministic, 24 | previous_trainer, fp16) 25 | self.max_num_epochs = 500 26 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/cascade/nnUNetTrainerV2CascadeFullRes_shorter_lowerLR.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2_CascadeFullRes import nnUNetTrainerV2CascadeFullRes 17 | 18 | 19 | class nnUNetTrainerV2CascadeFullRes_shorter_lowerLR(nnUNetTrainerV2CascadeFullRes): 20 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 21 | unpack_data=True, deterministic=True, previous_trainer="nnUNetTrainerV2", fp16=False): 22 | super().__init__(plans_file, fold, output_folder, dataset_directory, 23 | batch_dice, stage, unpack_data, deterministic, 24 | previous_trainer, fp16) 25 | self.max_num_epochs = 500 26 | self.initial_lr = 1e-3 27 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/copies/nnUNetTrainerV2_copies.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | 18 | 19 | # This stuff is just so that we can check stability of results. Training is nondeterministic and by renaming the trainer 20 | # class we can have several trained models coexist although the trainer is effectively the same 21 | 22 | 23 | class nnUNetTrainerV2_copy1(nnUNetTrainerV2): 24 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 25 | unpack_data=True, deterministic=True, fp16=False): 26 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 27 | deterministic, fp16) 28 | 29 | 30 | class nnUNetTrainerV2_copy2(nnUNetTrainerV2): 31 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 32 | unpack_data=True, deterministic=True, fp16=False): 33 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 34 | deterministic, fp16) 35 | 36 | 37 | class nnUNetTrainerV2_copy3(nnUNetTrainerV2): 38 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 39 | unpack_data=True, deterministic=True, fp16=False): 40 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 41 | deterministic, fp16) 42 | 43 | 44 | class nnUNetTrainerV2_copy4(nnUNetTrainerV2): 45 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 46 | unpack_data=True, deterministic=True, fp16=False): 47 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 48 | deterministic, fp16) 49 | 50 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/data_augmentation/nnUNetTrainerV2_DA2.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | 18 | 19 | class nnUNetTrainerV2_DA2(nnUNetTrainerV2): 20 | def setup_DA_params(self): 21 | super().setup_DA_params() 22 | 23 | self.data_aug_params["independent_scale_factor_for_each_axis"] = True 24 | 25 | if self.threeD: 26 | self.data_aug_params["rotation_p_per_axis"] = 0.5 27 | else: 28 | self.data_aug_params["rotation_p_per_axis"] = 1 29 | 30 | self.data_aug_params["do_additive_brightness"] = True 31 | 32 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/data_augmentation/nnUNetTrainerV2_independentScalePerAxis.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | 18 | 19 | class nnUNetTrainerV2_independentScalePerAxis(nnUNetTrainerV2): 20 | def setup_DA_params(self): 21 | super().setup_DA_params() 22 | self.data_aug_params["independent_scale_factor_for_each_axis"] = True 23 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/data_augmentation/nnUNetTrainerV2_noMirroring.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | 18 | 19 | class nnUNetTrainerV2_noMirroring(nnUNetTrainerV2): 20 | def validate(self, do_mirroring: bool = True, use_sliding_window: bool = True, 21 | step_size: float = 0.5, save_softmax: bool = True, use_gaussian: bool = True, overwrite: bool = True, 22 | validation_folder_name: str = 'validation_raw', debug: bool = False, all_in_gpu: bool = False, 23 | segmentation_export_kwargs: dict = None): 24 | """ 25 | We need to wrap this because we need to enforce self.network.do_ds = False for prediction 26 | 27 | :param do_mirroring: 28 | :param use_train_mode: 29 | :param use_sliding_window: 30 | :param step_size: 31 | :param save_softmax: 32 | :param use_gaussian: 33 | :param compute_global_dice: 34 | :param overwrite: 35 | :param validation_folder_name: 36 | :return: 37 | """ 38 | ds = self.network.do_ds 39 | if do_mirroring: 40 | print("WARNING! do_mirroring was True but we cannot do that because we trained without mirroring. " 41 | "do_mirroring was set to False") 42 | do_mirroring = False 43 | self.network.do_ds = False 44 | ret = super().validate(do_mirroring=do_mirroring, use_sliding_window=use_sliding_window, step_size=step_size, 45 | save_softmax=save_softmax, use_gaussian=use_gaussian, 46 | overwrite=overwrite, validation_folder_name=validation_folder_name, debug=debug, 47 | all_in_gpu=all_in_gpu, segmentation_export_kwargs=segmentation_export_kwargs) 48 | self.network.do_ds = ds 49 | return ret 50 | 51 | def setup_DA_params(self): 52 | super().setup_DA_params() 53 | self.data_aug_params["do_mirror"] = False 54 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/loss_function/nnUNetTrainerV2_ForceBD.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | 18 | 19 | class nnUNetTrainerV2_ForceBD(nnUNetTrainerV2): 20 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 21 | unpack_data=True, deterministic=True, fp16=False): 22 | batch_dice = True 23 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 24 | deterministic, fp16) 25 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/loss_function/nnUNetTrainerV2_ForceSD.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | 18 | 19 | class nnUNetTrainerV2_ForceSD(nnUNetTrainerV2): 20 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 21 | unpack_data=True, deterministic=True, fp16=False): 22 | batch_dice = False 23 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 24 | deterministic, fp16) 25 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/loss_function/nnUNetTrainerV2_Loss_CE.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | from nnunet.training.loss_functions.crossentropy import RobustCrossEntropyLoss 15 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 16 | 17 | 18 | class nnUNetTrainerV2_Loss_CE(nnUNetTrainerV2): 19 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 20 | unpack_data=True, deterministic=True, fp16=False): 21 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 22 | deterministic, fp16) 23 | self.loss = RobustCrossEntropyLoss() 24 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/loss_function/nnUNetTrainerV2_Loss_CEGDL.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | from nnunet.training.loss_functions.dice_loss import GDL_and_CE_loss 18 | 19 | 20 | class nnUNetTrainerV2_Loss_CEGDL(nnUNetTrainerV2): 21 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 22 | unpack_data=True, deterministic=True, fp16=False): 23 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 24 | deterministic, fp16) 25 | self.loss = GDL_and_CE_loss({'batch_dice': self.batch_dice, 'smooth': 1e-5, 'do_bg': False}, {}) 26 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/loss_function/nnUNetTrainerV2_Loss_Dice.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | from nnunet.training.loss_functions.dice_loss import SoftDiceLoss 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | 20 | 21 | class nnUNetTrainerV2_Loss_Dice(nnUNetTrainerV2): 22 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 23 | unpack_data=True, deterministic=True, fp16=False): 24 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 25 | deterministic, fp16) 26 | self.loss = SoftDiceLoss(**{'apply_nonlin': softmax_helper, 'batch_dice': self.batch_dice, 'smooth': 1e-5, 'do_bg': False}) 27 | 28 | 29 | class nnUNetTrainerV2_Loss_DicewithBG(nnUNetTrainerV2): 30 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 31 | unpack_data=True, deterministic=True, fp16=False): 32 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 33 | deterministic, fp16) 34 | self.loss = SoftDiceLoss(**{'apply_nonlin': softmax_helper, 'batch_dice': self.batch_dice, 'smooth': 1e-5, 'do_bg': True}) 35 | 36 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/loss_function/nnUNetTrainerV2_Loss_DiceTopK10.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | from nnunet.training.loss_functions.dice_loss import DC_and_topk_loss 18 | 19 | 20 | class nnUNetTrainerV2_Loss_DiceTopK10(nnUNetTrainerV2): 21 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 22 | unpack_data=True, deterministic=True, fp16=False): 23 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 24 | deterministic, fp16) 25 | self.loss = DC_and_topk_loss({'batch_dice': self.batch_dice, 'smooth': 1e-5, 'do_bg': False}, 26 | {'k': 10}) 27 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/loss_function/nnUNetTrainerV2_Loss_Dice_lr1en3.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNet_variants.loss_function.nnUNetTrainerV2_Loss_Dice import \ 17 | nnUNetTrainerV2_Loss_Dice, nnUNetTrainerV2_Loss_DicewithBG 18 | 19 | 20 | class nnUNetTrainerV2_Loss_Dice_LR1en3(nnUNetTrainerV2_Loss_Dice): 21 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 22 | unpack_data=True, deterministic=True, fp16=False): 23 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 24 | deterministic, fp16) 25 | self.initial_lr = 1e-3 26 | 27 | 28 | class nnUNetTrainerV2_Loss_DicewithBG_LR1en3(nnUNetTrainerV2_Loss_DicewithBG): 29 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 30 | unpack_data=True, deterministic=True, fp16=False): 31 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 32 | deterministic, fp16) 33 | self.initial_lr = 1e-3 34 | 35 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/loss_function/nnUNetTrainerV2_Loss_Dice_squared.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | from nnunet.training.loss_functions.dice_loss import SoftDiceLossSquared 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | 20 | 21 | class nnUNetTrainerV2_Loss_Dice_squared(nnUNetTrainerV2): 22 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 23 | unpack_data=True, deterministic=True, fp16=False): 24 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 25 | deterministic, fp16) 26 | self.initial_lr = 1e-3 27 | self.loss = SoftDiceLossSquared(**{'apply_nonlin': softmax_helper, 'batch_dice': self.batch_dice, 'smooth': 1e-5, 'do_bg': False}) 28 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/loss_function/nnUNetTrainerV2_Loss_MCC.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | from nnunet.training.loss_functions.dice_loss import MCCLoss 18 | from nnunet.utilities.nd_softmax import softmax_helper 19 | 20 | 21 | class nnUNetTrainerV2_Loss_MCC(nnUNetTrainerV2): 22 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 23 | unpack_data=True, deterministic=True, fp16=False): 24 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 25 | deterministic, fp16) 26 | self.initial_lr = 1e-3 27 | self.loss = MCCLoss(apply_nonlin=softmax_helper, batch_mcc=self.batch_dice, do_bg=True, smooth=0.0) 28 | 29 | 30 | class nnUNetTrainerV2_Loss_MCCnoBG(nnUNetTrainerV2): 31 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 32 | unpack_data=True, deterministic=True, fp16=False): 33 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 34 | deterministic, fp16) 35 | self.initial_lr = 1e-3 36 | self.loss = MCCLoss(apply_nonlin=softmax_helper, batch_mcc=self.batch_dice, do_bg=False, smooth=0.0) 37 | 38 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/loss_function/nnUNetTrainerV2_Loss_TopK10.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | from nnunet.training.loss_functions.TopK_loss import TopKLoss 18 | 19 | 20 | class nnUNetTrainerV2_Loss_TopK10(nnUNetTrainerV2): 21 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 22 | unpack_data=True, deterministic=True, fp16=False): 23 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 24 | deterministic, fp16) 25 | self.loss = TopKLoss(k=10) 26 | 27 | 28 | nnUNetTrainerV2_Loss_TopK10_copy1 = nnUNetTrainerV2_Loss_TopK10 29 | nnUNetTrainerV2_Loss_TopK10_copy2 = nnUNetTrainerV2_Loss_TopK10 30 | nnUNetTrainerV2_Loss_TopK10_copy3 = nnUNetTrainerV2_Loss_TopK10 31 | nnUNetTrainerV2_Loss_TopK10_copy4 = nnUNetTrainerV2_Loss_TopK10 32 | 33 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/loss_function/nnUNetTrainerV2_graduallyTransitionFromCEToDice.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.loss_functions.deep_supervision import MultipleOutputLoss2 17 | from nnunet.training.loss_functions.dice_loss import DC_and_CE_loss 18 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 19 | 20 | 21 | class nnUNetTrainerV2_graduallyTransitionFromCEToDice(nnUNetTrainerV2): 22 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 23 | unpack_data=True, deterministic=True, fp16=False): 24 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 25 | deterministic, fp16) 26 | self.loss = DC_and_CE_loss({'batch_dice': self.batch_dice, 'smooth': 1e-5, 'do_bg': False}, {}, weight_ce=2, weight_dice=0) 27 | 28 | def update_loss(self): 29 | # we train the first 500 epochs with CE, then transition to Dice between 500 and 750. The last 250 epochs will be Dice only 30 | 31 | if self.epoch <= 500: 32 | weight_ce = 2 33 | weight_dice = 0 34 | elif 500 < self.epoch <= 750: 35 | weight_ce = 2 - 2 / 250 * (self.epoch - 500) 36 | weight_dice = 0 + 2 / 250 * (self.epoch - 500) 37 | elif 750 < self.epoch <= self.max_num_epochs: 38 | weight_ce = 0 39 | weight_dice = 2 40 | else: 41 | raise RuntimeError("Invalid epoch: %d" % self.epoch) 42 | 43 | self.print_to_log_file("weight ce", weight_ce, "weight dice", weight_dice) 44 | 45 | self.loss = DC_and_CE_loss({'batch_dice': self.batch_dice, 'smooth': 1e-5, 'do_bg': False}, {}, weight_ce=weight_ce, 46 | weight_dice=weight_dice) 47 | 48 | self.loss = MultipleOutputLoss2(self.loss, self.ds_loss_weights) 49 | 50 | def on_epoch_end(self): 51 | ret = super().on_epoch_end() 52 | self.update_loss() 53 | return ret 54 | 55 | def load_checkpoint_ram(self, checkpoint, train=True): 56 | ret = super().load_checkpoint_ram(checkpoint, train) 57 | self.update_loss() 58 | return ret 59 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/nnUNetTrainerCE.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | from nnunet.training.loss_functions.crossentropy import RobustCrossEntropyLoss 15 | from nnunet.training.network_training.nnUNetTrainer import nnUNetTrainer 16 | 17 | 18 | class nnUNetTrainerCE(nnUNetTrainer): 19 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 20 | unpack_data=True, deterministic=True, fp16=False): 21 | super(nnUNetTrainerCE, self).__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, 22 | unpack_data, deterministic, fp16) 23 | self.loss = RobustCrossEntropyLoss() 24 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_Adam.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import torch 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | 19 | 20 | class nnUNetTrainerV2_Adam(nnUNetTrainerV2): 21 | 22 | def initialize_optimizer_and_scheduler(self): 23 | self.optimizer = torch.optim.Adam(self.network.parameters(), self.initial_lr, weight_decay=self.weight_decay, amsgrad=True) 24 | self.lr_scheduler = None 25 | 26 | 27 | nnUNetTrainerV2_Adam_copy1 = nnUNetTrainerV2_Adam 28 | nnUNetTrainerV2_Adam_copy2 = nnUNetTrainerV2_Adam 29 | nnUNetTrainerV2_Adam_copy3 = nnUNetTrainerV2_Adam 30 | nnUNetTrainerV2_Adam_copy4 = nnUNetTrainerV2_Adam 31 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_Adam_ReduceOnPlateau.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import torch 17 | from nnunet.training.network_training.nnUNetTrainer import nnUNetTrainer 18 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 19 | from torch.optim import lr_scheduler 20 | 21 | 22 | class nnUNetTrainerV2_Adam_ReduceOnPlateau(nnUNetTrainerV2): 23 | """ 24 | Same schedule as nnUNetTrainer 25 | """ 26 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 27 | unpack_data=True, deterministic=True, fp16=False): 28 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 29 | deterministic, fp16) 30 | self.initial_lr = 3e-4 31 | 32 | def initialize_optimizer_and_scheduler(self): 33 | assert self.network is not None, "self.initialize_network must be called first" 34 | self.optimizer = torch.optim.Adam(self.network.parameters(), self.initial_lr, weight_decay=self.weight_decay, 35 | amsgrad=True) 36 | self.lr_scheduler = lr_scheduler.ReduceLROnPlateau(self.optimizer, mode='min', factor=0.2, 37 | patience=self.lr_scheduler_patience, 38 | verbose=True, threshold=self.lr_scheduler_eps, 39 | threshold_mode="abs") 40 | 41 | def maybe_update_lr(self, epoch=None): 42 | # maybe update learning rate 43 | if self.lr_scheduler is not None: 44 | assert isinstance(self.lr_scheduler, (lr_scheduler.ReduceLROnPlateau, lr_scheduler._LRScheduler)) 45 | 46 | if isinstance(self.lr_scheduler, lr_scheduler.ReduceLROnPlateau): 47 | # lr scheduler is updated with moving average val loss. should be more robust 48 | if self.epoch > 0 and self.train_loss_MA is not None: # otherwise self.train_loss_MA is None 49 | self.lr_scheduler.step(self.train_loss_MA) 50 | else: 51 | self.lr_scheduler.step(self.epoch + 1) 52 | self.print_to_log_file("lr is now (scheduler) %s" % str(self.optimizer.param_groups[0]['lr'])) 53 | 54 | def on_epoch_end(self): 55 | return nnUNetTrainer.on_epoch_end(self) 56 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_Adam_lr_3en4.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNet_variants.optimizer_and_lr.nnUNetTrainerV2_Adam import nnUNetTrainerV2_Adam 17 | 18 | 19 | class nnUNetTrainerV2_Adam_nnUNetTrainerlr(nnUNetTrainerV2_Adam): 20 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 21 | unpack_data=True, deterministic=True, fp16=False): 22 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 23 | deterministic, fp16) 24 | self.initial_lr = 3e-4 25 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_Ranger_lr1en2.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | from nnunet.training.optimizer.ranger import Ranger 18 | 19 | 20 | class nnUNetTrainerV2_Ranger_lr1en2(nnUNetTrainerV2): 21 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 22 | unpack_data=True, deterministic=True, fp16=False): 23 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 24 | deterministic, fp16) 25 | self.initial_lr = 1e-2 26 | 27 | def initialize_optimizer_and_scheduler(self): 28 | self.optimizer = Ranger(self.network.parameters(), self.initial_lr, k=6, N_sma_threshhold=5, 29 | weight_decay=self.weight_decay) 30 | self.lr_scheduler = None 31 | 32 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_Ranger_lr3en3.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | from nnunet.training.optimizer.ranger import Ranger 18 | 19 | 20 | class nnUNetTrainerV2_Ranger_lr3en3(nnUNetTrainerV2): 21 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 22 | unpack_data=True, deterministic=True, fp16=False): 23 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 24 | deterministic, fp16) 25 | self.initial_lr = 3e-3 26 | 27 | def initialize_optimizer_and_scheduler(self): 28 | self.optimizer = Ranger(self.network.parameters(), self.initial_lr, k=6, N_sma_threshhold=5, 29 | weight_decay=self.weight_decay) 30 | self.lr_scheduler = None 31 | 32 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_Ranger_lr3en4.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | from nnunet.training.optimizer.ranger import Ranger 18 | 19 | 20 | class nnUNetTrainerV2_Ranger_lr3en4(nnUNetTrainerV2): 21 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 22 | unpack_data=True, deterministic=True, fp16=False): 23 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 24 | deterministic, fp16) 25 | self.initial_lr = 3e-4 26 | 27 | def initialize_optimizer_and_scheduler(self): 28 | self.optimizer = Ranger(self.network.parameters(), self.initial_lr, k=6, N_sma_threshhold=5, 29 | weight_decay=self.weight_decay) 30 | self.lr_scheduler = None 31 | 32 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_SGD_ReduceOnPlateau.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import torch 17 | from nnunet.training.network_training.nnUNetTrainer import nnUNetTrainer 18 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 19 | from torch.optim import lr_scheduler 20 | 21 | 22 | class nnUNetTrainerV2_SGD_ReduceOnPlateau(nnUNetTrainerV2): 23 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 24 | unpack_data=True, deterministic=True, fp16=False): 25 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 26 | deterministic, fp16) 27 | 28 | def initialize_optimizer_and_scheduler(self): 29 | self.optimizer = torch.optim.SGD(self.network.parameters(), self.initial_lr, weight_decay=self.weight_decay, 30 | momentum=0.99, nesterov=True) 31 | self.lr_scheduler = lr_scheduler.ReduceLROnPlateau(self.optimizer, mode='min', factor=0.2, 32 | patience=self.lr_scheduler_patience, 33 | verbose=True, threshold=self.lr_scheduler_eps, 34 | threshold_mode="abs") 35 | 36 | def maybe_update_lr(self, epoch=None): 37 | # maybe update learning rate 38 | if self.lr_scheduler is not None: 39 | assert isinstance(self.lr_scheduler, (lr_scheduler.ReduceLROnPlateau, lr_scheduler._LRScheduler)) 40 | 41 | if isinstance(self.lr_scheduler, lr_scheduler.ReduceLROnPlateau): 42 | # lr scheduler is updated with moving average val loss. should be more robust 43 | if self.epoch > 0: # otherwise self.train_loss_MA is None 44 | self.lr_scheduler.step(self.train_loss_MA) 45 | else: 46 | self.lr_scheduler.step(self.epoch + 1) 47 | self.print_to_log_file("lr is now (scheduler) %s" % str(self.optimizer.param_groups[0]['lr'])) 48 | 49 | def on_epoch_end(self): 50 | return nnUNetTrainer.on_epoch_end(self) 51 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_SGD_fixedSchedule.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | 18 | 19 | class nnUNetTrainerV2_SGD_fixedSchedule(nnUNetTrainerV2): 20 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 21 | unpack_data=True, deterministic=True, fp16=False): 22 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 23 | deterministic, fp16) 24 | 25 | def maybe_update_lr(self, epoch=None): 26 | if epoch is None: 27 | ep = self.epoch + 1 28 | else: 29 | ep = epoch 30 | 31 | if 0 <= ep < 500: 32 | new_lr = self.initial_lr 33 | elif 500 <= ep < 675: 34 | new_lr = self.initial_lr * 0.1 35 | elif 675 <= ep < 850: 36 | new_lr = self.initial_lr * 0.01 37 | elif ep >= 850: 38 | new_lr = self.initial_lr * 0.001 39 | else: 40 | raise RuntimeError("Really unexpected things happened, ep=%d" % ep) 41 | 42 | self.optimizer.param_groups[0]['lr'] = new_lr 43 | self.print_to_log_file("lr:", self.optimizer.param_groups[0]['lr']) 44 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_SGD_fixedSchedule2.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.learning_rate.poly_lr import poly_lr 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | 19 | 20 | class nnUNetTrainerV2_SGD_fixedSchedule2(nnUNetTrainerV2): 21 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 22 | unpack_data=True, deterministic=True, fp16=False): 23 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 24 | deterministic, fp16) 25 | 26 | def maybe_update_lr(self, epoch=None): 27 | """ 28 | here we go one step, then use polyLR 29 | :param epoch: 30 | :return: 31 | """ 32 | if epoch is None: 33 | ep = self.epoch + 1 34 | else: 35 | ep = epoch 36 | 37 | if 0 <= ep < 500: 38 | new_lr = self.initial_lr 39 | elif 500 <= ep < 675: 40 | new_lr = self.initial_lr * 0.1 41 | elif ep >= 675: 42 | new_lr = poly_lr(ep - 675, self.max_num_epochs - 675, self.initial_lr * 0.1, 0.9) 43 | else: 44 | raise RuntimeError("Really unexpected things happened, ep=%d" % ep) 45 | 46 | self.optimizer.param_groups[0]['lr'] = new_lr 47 | self.print_to_log_file("lr:", self.optimizer.param_groups[0]['lr']) 48 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_SGD_lrs.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | 18 | 19 | class nnUNetTrainerV2_SGD_lr1en1(nnUNetTrainerV2): 20 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 21 | unpack_data=True, deterministic=True, fp16=False): 22 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 23 | deterministic, fp16) 24 | self.initial_lr = 1e-1 25 | 26 | 27 | class nnUNetTrainerV2_SGD_lr1en3(nnUNetTrainerV2): 28 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 29 | unpack_data=True, deterministic=True, fp16=False): 30 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 31 | deterministic, fp16) 32 | self.initial_lr = 1e-3 33 | 34 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_fp16.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | 18 | 19 | class nnUNetTrainerV2_fp16(nnUNetTrainerV2): 20 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 21 | unpack_data=True, deterministic=True, fp16=False): 22 | assert fp16, "This one only accepts fp16=True" 23 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 24 | deterministic, fp16) 25 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_momentum09.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import torch 17 | 18 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 19 | 20 | 21 | class nnUNetTrainerV2_momentum09(nnUNetTrainerV2): 22 | def initialize_optimizer_and_scheduler(self): 23 | assert self.network is not None, "self.initialize_network must be called first" 24 | self.optimizer = torch.optim.SGD(self.network.parameters(), self.initial_lr, weight_decay=self.weight_decay, 25 | momentum=0.9, nesterov=True) 26 | self.lr_scheduler = None 27 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_momentum095.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import torch 17 | 18 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 19 | 20 | 21 | class nnUNetTrainerV2_momentum095(nnUNetTrainerV2): 22 | def initialize_optimizer_and_scheduler(self): 23 | assert self.network is not None, "self.initialize_network must be called first" 24 | self.optimizer = torch.optim.SGD(self.network.parameters(), self.initial_lr, weight_decay=self.weight_decay, 25 | momentum=0.95, nesterov=True) 26 | self.lr_scheduler = None 27 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_momentum098.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import torch 17 | 18 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 19 | 20 | 21 | class nnUNetTrainerV2_momentum098(nnUNetTrainerV2): 22 | def initialize_optimizer_and_scheduler(self): 23 | assert self.network is not None, "self.initialize_network must be called first" 24 | self.optimizer = torch.optim.SGD(self.network.parameters(), self.initial_lr, weight_decay=self.weight_decay, 25 | momentum=0.98, nesterov=True) 26 | self.lr_scheduler = None 27 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_momentum09in2D.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import torch 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | 19 | 20 | class nnUNetTrainerV2_momentum09in2D(nnUNetTrainerV2): 21 | def initialize_optimizer_and_scheduler(self): 22 | if self.threeD: 23 | momentum = 0.99 24 | else: 25 | momentum = 0.9 26 | assert self.network is not None, "self.initialize_network must be called first" 27 | self.optimizer = torch.optim.SGD(self.network.parameters(), self.initial_lr, weight_decay=self.weight_decay, 28 | momentum=momentum, nesterov=True) 29 | self.lr_scheduler = None 30 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_reduceMomentumDuringTraining.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import torch 17 | 18 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 19 | 20 | 21 | class nnUNetTrainerV2_reduceMomentumDuringTraining(nnUNetTrainerV2): 22 | """ 23 | This implementation will not work with LR scheduler!!!!!!!!!! 24 | 25 | After epoch 800, linearly decrease momentum from 0.99 to 0.9 26 | """ 27 | def initialize_optimizer_and_scheduler(self): 28 | current_momentum = 0.99 29 | min_momentum = 0.9 30 | 31 | if self.epoch > 800: 32 | current_momentum = current_momentum - (current_momentum - min_momentum) / 200 * (self.epoch - 800) 33 | 34 | self.print_to_log_file("current momentum", current_momentum) 35 | assert self.network is not None, "self.initialize_network must be called first" 36 | if self.optimizer is None: 37 | self.optimizer = torch.optim.SGD(self.network.parameters(), self.initial_lr, weight_decay=self.weight_decay, 38 | momentum=0.99, nesterov=True) 39 | else: 40 | # can't reinstantiate because that would break NVIDIA AMP 41 | self.optimizer.param_groups[0]["momentum"] = current_momentum 42 | self.lr_scheduler = None 43 | 44 | def on_epoch_end(self): 45 | self.initialize_optimizer_and_scheduler() 46 | return super().on_epoch_end() 47 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/optimizer_and_lr/nnUNetTrainerV2_warmup.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 17 | 18 | 19 | class nnUNetTrainerV2_warmup(nnUNetTrainerV2): 20 | def __init__(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None, 21 | unpack_data=True, deterministic=True, fp16=False): 22 | super().__init__(plans_file, fold, output_folder, dataset_directory, batch_dice, stage, unpack_data, 23 | deterministic, fp16) 24 | self.max_num_epochs = 1050 25 | 26 | def maybe_update_lr(self, epoch=None): 27 | if self.epoch < 50: 28 | # epoch 49 is max 29 | # we increase lr linearly from 0 to initial_lr 30 | lr = (self.epoch + 1) / 50 * self.initial_lr 31 | self.optimizer.param_groups[0]['lr'] = lr 32 | self.print_to_log_file("epoch:", self.epoch, "lr:", lr) 33 | else: 34 | if epoch is not None: 35 | ep = epoch - 49 36 | else: 37 | ep = self.epoch - 49 38 | assert ep > 0, "epoch must be >0" 39 | return super().maybe_update_lr(ep) 40 | -------------------------------------------------------------------------------- /nnUNet/nnunet/training/network_training/nnUNet_variants/resampling/nnUNetTrainerV2_resample33.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from nnunet.inference.segmentation_export import save_segmentation_nifti_from_softmax 17 | from nnunet.training.network_training.nnUNetTrainerV2 import nnUNetTrainerV2 18 | 19 | 20 | class nnUNetTrainerV2_resample33(nnUNetTrainerV2): 21 | def validate(self, do_mirroring: bool = True, use_sliding_window: bool = True, 22 | step_size: float = 0.5, save_softmax: bool = True, use_gaussian: bool = True, overwrite: bool = True, 23 | validation_folder_name: str = 'validation_raw', debug: bool = False, all_in_gpu: bool = False, 24 | segmentation_export_kwargs: dict = None): 25 | return super().validate(do_mirroring, use_sliding_window, step_size, save_softmax, use_gaussian, 26 | overwrite, validation_folder_name, debug, all_in_gpu, segmentation_export_kwargs) 27 | 28 | def preprocess_predict_nifti(self, input_files, output_file=None, softmax_ouput_file=None, 29 | mixed_precision: bool = True): 30 | """ 31 | Use this to predict new data 32 | :param input_files: 33 | :param output_file: 34 | :param softmax_ouput_file: 35 | :param mixed_precision: 36 | :return: 37 | """ 38 | print("preprocessing...") 39 | d, s, properties = self.preprocess_patient(input_files) 40 | print("predicting...") 41 | pred = self.predict_preprocessed_data_return_seg_and_softmax(d, do_mirroring=self.data_aug_params["do_mirror"], 42 | mirror_axes=self.data_aug_params['mirror_axes'], 43 | use_sliding_window=True, step_size=0.5, 44 | use_gaussian=True, pad_border_mode='constant', 45 | pad_kwargs={'constant_values': 0}, 46 | all_in_gpu=True, 47 | mixed_precision=mixed_precision)[1] 48 | pred = pred.transpose([0] + [i + 1 for i in self.transpose_backward]) 49 | 50 | print("resampling to original spacing and nifti export...") 51 | save_segmentation_nifti_from_softmax(pred, output_file, properties, 3, None, None, None, softmax_ouput_file, 52 | None, force_separate_z=False, interpolation_order_z=3) 53 | print("done") 54 | -------------------------------------------------------------------------------- /nnUNet/nnunet/utilities/__init__.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from . import * -------------------------------------------------------------------------------- /nnUNet/nnunet/utilities/distributed.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import torch 17 | from torch import distributed 18 | from torch import autograd 19 | from torch.nn.parallel import DistributedDataParallel as DDP 20 | 21 | 22 | def print_if_rank0(*args): 23 | if distributed.get_rank() == 0: 24 | print(*args) 25 | 26 | 27 | class awesome_allgather_function(autograd.Function): 28 | @staticmethod 29 | def forward(ctx, input): 30 | world_size = distributed.get_world_size() 31 | # create a destination list for the allgather. I'm assuming you're gathering from 3 workers. 32 | allgather_list = [torch.empty_like(input) for _ in range(world_size)] 33 | #if distributed.get_rank() == 0: 34 | # import IPython;IPython.embed() 35 | distributed.all_gather(allgather_list, input) 36 | return torch.cat(allgather_list, dim=0) 37 | 38 | @staticmethod 39 | def backward(ctx, grad_output): 40 | #print_if_rank0("backward grad_output len", len(grad_output)) 41 | #print_if_rank0("backward grad_output shape", grad_output.shape) 42 | grads_per_rank = grad_output.shape[0] // distributed.get_world_size() 43 | rank = distributed.get_rank() 44 | # We'll receive gradients for the entire catted forward output, so to mimic DataParallel, 45 | # return only the slice that corresponds to this process's input: 46 | sl = slice(rank * grads_per_rank, (rank + 1) * grads_per_rank) 47 | #print("worker", rank, "backward slice", sl) 48 | return grad_output[sl] 49 | 50 | 51 | if __name__ == "__main__": 52 | import torch.distributed as dist 53 | import argparse 54 | from torch import nn 55 | from torch.optim import Adam 56 | 57 | argumentparser = argparse.ArgumentParser() 58 | argumentparser.add_argument("--local_rank", type=int) 59 | args = argumentparser.parse_args() 60 | 61 | torch.cuda.set_device(args.local_rank) 62 | dist.init_process_group(backend='nccl', init_method='env://') 63 | 64 | rnd = torch.rand((5, 2)).cuda() 65 | 66 | rnd_gathered = awesome_allgather_function.apply(rnd) 67 | print("gathering random tensors\nbefore\b", rnd, "\nafter\n", rnd_gathered) 68 | 69 | # so far this works as expected 70 | print("now running a DDP model") 71 | c = nn.Conv2d(2, 3, 3, 1, 1, 1, 1, True).cuda() 72 | c = DDP(c) 73 | opt = Adam(c.parameters()) 74 | 75 | bs = 5 76 | if dist.get_rank() == 0: 77 | bs = 4 78 | inp = torch.rand((bs, 2, 5, 5)).cuda() 79 | 80 | out = c(inp) 81 | print("output_shape", out.shape) 82 | 83 | out_gathered = awesome_allgather_function.apply(out) 84 | print("output_shape_after_gather", out_gathered.shape) 85 | # this also works 86 | 87 | loss = out_gathered.sum() 88 | loss.backward() 89 | opt.step() 90 | -------------------------------------------------------------------------------- /nnUNet/nnunet/utilities/file_endings.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from batchgenerators.utilities.file_and_folder_operations import * 17 | 18 | 19 | def remove_trailing_slash(filename: str): 20 | while filename.endswith('/'): 21 | filename = filename[:-1] 22 | return filename 23 | 24 | 25 | def maybe_add_0000_to_all_niigz(folder): 26 | nii_gz = subfiles(folder, suffix='.nii.gz') 27 | for n in nii_gz: 28 | n = remove_trailing_slash(n) 29 | if not n.endswith('_0000.nii.gz'): 30 | os.rename(n, n[:-7] + '_0000.nii.gz') 31 | -------------------------------------------------------------------------------- /nnUNet/nnunet/utilities/folder_names.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from batchgenerators.utilities.file_and_folder_operations import * 17 | from nnunet.paths import network_training_output_dir 18 | 19 | 20 | def get_output_folder_name(model: str, task: str = None, trainer: str = None, plans: str = None, fold: int = None, 21 | overwrite_training_output_dir: str = None): 22 | """ 23 | Retrieves the correct output directory for the nnU-Net model described by the input parameters 24 | 25 | :param model: 26 | :param task: 27 | :param trainer: 28 | :param plans: 29 | :param fold: 30 | :param overwrite_training_output_dir: 31 | :return: 32 | """ 33 | assert model in ["2d", "3d_cascade_fullres", '3d_fullres', '3d_lowres'] 34 | 35 | if overwrite_training_output_dir is not None: 36 | tr_dir = overwrite_training_output_dir 37 | else: 38 | tr_dir = network_training_output_dir 39 | 40 | current = join(tr_dir, model) 41 | if task is not None: 42 | current = join(current, task) 43 | if trainer is not None and plans is not None: 44 | current = join(current, trainer + "__" + plans) 45 | if fold is not None: 46 | current = join(current, "fold_%d" % fold) 47 | return current 48 | -------------------------------------------------------------------------------- /nnUNet/nnunet/utilities/nd_softmax.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | import torch 16 | from torch import nn 17 | import torch.nn.functional as F 18 | 19 | 20 | softmax_helper = lambda x: F.softmax(x, 1) 21 | 22 | -------------------------------------------------------------------------------- /nnUNet/nnunet/utilities/one_hot_encoding.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | import numpy as np 16 | 17 | 18 | def to_one_hot(seg, all_seg_labels=None): 19 | if all_seg_labels is None: 20 | all_seg_labels = np.unique(seg) 21 | result = np.zeros((len(all_seg_labels), *seg.shape), dtype=seg.dtype) 22 | for i, l in enumerate(all_seg_labels): 23 | result[i][seg == l] = 1 24 | return result 25 | -------------------------------------------------------------------------------- /nnUNet/nnunet/utilities/random_stuff.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | class no_op(object): 17 | def __enter__(self): 18 | pass 19 | 20 | def __exit__(self, *args): 21 | pass 22 | -------------------------------------------------------------------------------- /nnUNet/nnunet/utilities/recursive_delete_npz.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from batchgenerators.utilities.file_and_folder_operations import * 17 | import argparse 18 | import os 19 | 20 | 21 | def recursive_delete_npz(current_directory: str): 22 | npz_files = subfiles(current_directory, join=True, suffix=".npz") 23 | npz_files = [i for i in npz_files if not i.endswith("segFromPrevStage.npz")] # to be extra safe 24 | _ = [os.remove(i) for i in npz_files] 25 | for d in subdirs(current_directory, join=False): 26 | if d != "pred_next_stage": 27 | recursive_delete_npz(join(current_directory, d)) 28 | 29 | 30 | if __name__ == "__main__": 31 | parser = argparse.ArgumentParser(usage="USE THIS RESPONSIBLY! DANGEROUS! I (Fabian) use this to remove npz files " 32 | "after I ran figure_out_what_to_submit") 33 | parser.add_argument("-f", help="folder", required=True) 34 | 35 | args = parser.parse_args() 36 | 37 | recursive_delete_npz(args.f) 38 | -------------------------------------------------------------------------------- /nnUNet/nnunet/utilities/recursive_rename_taskXX_to_taskXXX.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | from batchgenerators.utilities.file_and_folder_operations import * 17 | import os 18 | 19 | 20 | def recursive_rename(folder): 21 | s = subdirs(folder, join=False) 22 | for ss in s: 23 | if ss.startswith("Task") and ss.find("_") == 6: 24 | task_id = int(ss[4:6]) 25 | name = ss[7:] 26 | os.rename(join(folder, ss), join(folder, "Task%03.0d_" % task_id + name)) 27 | s = subdirs(folder, join=True) 28 | for ss in s: 29 | recursive_rename(ss) 30 | 31 | if __name__ == "__main__": 32 | recursive_rename("/media/fabian/Results/nnUNet") 33 | recursive_rename("/media/fabian/nnunet") 34 | recursive_rename("/media/fabian/My Book/MedicalDecathlon") 35 | recursive_rename("/home/fabian/drives/datasets/nnUNet_raw") 36 | recursive_rename("/home/fabian/drives/datasets/nnUNet_preprocessed") 37 | recursive_rename("/home/fabian/drives/datasets/nnUNet_testSets") 38 | recursive_rename("/home/fabian/drives/datasets/results/nnUNet") 39 | recursive_rename("/home/fabian/drives/e230-dgx2-1-data_fabian/Decathlon_raw") 40 | recursive_rename("/home/fabian/drives/e230-dgx2-1-data_fabian/nnUNet_preprocessed") 41 | 42 | -------------------------------------------------------------------------------- /nnUNet/nnunet/utilities/sitk_stuff.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | 16 | import SimpleITK as sitk 17 | 18 | 19 | def copy_geometry(image: sitk.Image, ref: sitk.Image): 20 | image.SetOrigin(ref.GetOrigin()) 21 | image.SetDirection(ref.GetDirection()) 22 | image.SetSpacing(ref.GetSpacing()) 23 | return image 24 | -------------------------------------------------------------------------------- /nnUNet/nnunet/utilities/tensor_utilities.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | import numpy as np 16 | import torch 17 | from torch import nn 18 | 19 | 20 | def sum_tensor(inp, axes, keepdim=False): 21 | axes = np.unique(axes).astype(int) 22 | if keepdim: 23 | for ax in axes: 24 | inp = inp.sum(int(ax), keepdim=True) 25 | else: 26 | for ax in sorted(axes, reverse=True): 27 | inp = inp.sum(int(ax)) 28 | return inp 29 | 30 | 31 | def mean_tensor(inp, axes, keepdim=False): 32 | axes = np.unique(axes).astype(int) 33 | if keepdim: 34 | for ax in axes: 35 | inp = inp.mean(int(ax), keepdim=True) 36 | else: 37 | for ax in sorted(axes, reverse=True): 38 | inp = inp.mean(int(ax)) 39 | return inp 40 | 41 | 42 | def flip(x, dim): 43 | """ 44 | flips the tensor at dimension dim (mirroring!) 45 | :param x: 46 | :param dim: 47 | :return: 48 | """ 49 | indices = [slice(None)] * x.dim() 50 | indices[dim] = torch.arange(x.size(dim) - 1, -1, -1, 51 | dtype=torch.long, device=x.device) 52 | return x[tuple(indices)] 53 | 54 | 55 | -------------------------------------------------------------------------------- /nnUNet/nnunet/utilities/to_torch.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | 15 | import torch 16 | 17 | 18 | def maybe_to_torch(d): 19 | if isinstance(d, list): 20 | d = [maybe_to_torch(i) if not isinstance(i, torch.Tensor) else i for i in d] 21 | elif not isinstance(d, torch.Tensor): 22 | d = torch.from_numpy(d).float() 23 | return d 24 | 25 | 26 | def to_cuda(data, non_blocking=True, gpu_id=0): 27 | if isinstance(data, list): 28 | data = [i.cuda(gpu_id, non_blocking=non_blocking) for i in data] 29 | else: 30 | data = data.cuda(gpu_id, non_blocking=True) 31 | return data 32 | -------------------------------------------------------------------------------- /nnUNet/setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup, find_namespace_packages 2 | 3 | setup(name='nnunet', 4 | packages=find_namespace_packages(include=["nnunet", "nnunet.*"]), 5 | version='1.6.6', 6 | description='nnU-Net. Framework for out-of-the box biomedical image segmentation.', 7 | url='https://github.com/MIC-DKFZ/nnUNet', 8 | author='Division of Medical Image Computing, German Cancer Research Center', 9 | author_email='f.isensee@dkfz-heidelberg.de', 10 | license='Apache License Version 2.0, January 2004', 11 | install_requires=[ 12 | "tqdm", 13 | "dicom2nifti", 14 | "scikit-image>=0.14", 15 | "medpy", 16 | "scipy", 17 | "batchgenerators>=0.21", 18 | "numpy", 19 | "sklearn", 20 | "SimpleITK", 21 | "pandas", 22 | "requests", 23 | "nibabel", 'tifffile' 24 | ], 25 | entry_points={ 26 | 'console_scripts': [ 27 | 'nnUNet_convert_decathlon_task = nnunet.experiment_planning.nnUNet_convert_decathlon_task:main', 28 | 'nnUNet_plan_and_preprocess = nnunet.experiment_planning.nnUNet_plan_and_preprocess:main', 29 | 'nnUNet_train = nnunet.run.run_training:main', 30 | 'nnUNet_train_DP = nnunet.run.run_training_DP:main', 31 | 'nnUNet_train_DDP = nnunet.run.run_training_DDP:main', 32 | 'nnUNet_predict = nnunet.inference.predict_simple:main', 33 | 'nnUNet_ensemble = nnunet.inference.ensemble_predictions:main', 34 | 'nnUNet_find_best_configuration = nnunet.evaluation.model_selection.figure_out_what_to_submit:main', 35 | 'nnUNet_print_available_pretrained_models = nnunet.inference.pretrained_models.download_pretrained_model:print_available_pretrained_models', 36 | 'nnUNet_print_pretrained_model_info = nnunet.inference.pretrained_models.download_pretrained_model:print_pretrained_model_requirements', 37 | 'nnUNet_download_pretrained_model = nnunet.inference.pretrained_models.download_pretrained_model:download_by_name', 38 | 'nnUNet_download_pretrained_model_by_url = nnunet.inference.pretrained_models.download_pretrained_model:download_by_url', 39 | 'nnUNet_determine_postprocessing = nnunet.postprocessing.consolidate_postprocessing_simple:main', 40 | 'nnUNet_export_model_to_zip = nnunet.inference.pretrained_models.collect_pretrained_models:export_entry_point', 41 | 'nnUNet_install_pretrained_model_from_zip = nnunet.inference.pretrained_models.download_pretrained_model:install_from_zip_entry_point', 42 | 'nnUNet_change_trainer_class = nnunet.inference.change_trainer:main', 43 | 'nnUNet_evaluate_folder = nnunet.evaluation.evaluator:nnunet_evaluate_folder' 44 | ], 45 | }, 46 | keywords=['deep learning', 'image segmentation', 'medical image analysis', 47 | 'medical image segmentation', 'nnU-Net', 'nnunet'] 48 | ) 49 | --------------------------------------------------------------------------------