def __init__(self, server_env=False):
#########################
# Preprocessing #
#########################
self.root_dir = '/home/matthew/datasets/platelet-instance-3d'
self.min_volume = 100
#########################
# I/O #
#########################
# Either 'cell' or 'organelle'
self.label_type = 'organelle'
# one out of [2, 3]. dimension the model operates in.
self.dim = 3
# one out of ['mrcnn', 'retina_net', 'retina_unet', 'detection_unet', 'ufrcnn'].
self.model = 'mrcnn'
DefaultConfigs.__init__(self, self.model, server_env, self.dim)
# int [0 < dataset_size]. select n patients from dataset for prototyping.
self.select_prototype_subset = None
self.hold_out_test_set = True
# including val set. will be 3/4 train, 1/4 val.
self.n_train_val_data = 1
# path to preprocessed data.
self.input_df_name = 'info_df.pickle'
self.pp_name = os.path.join('mdt', self.label_type, 'train')
self.pp_data_path = os.path.join(self.root_dir, self.pp_name)
self.pp_test_name = os.path.join('mdt', self.label_type, 'test')
self.pp_test_data_path = os.path.join(self.root_dir, self.pp_test_name)
# settings for deployment in cloud.
if server_env:
# path to preprocessed data.
pp_root_dir = '/datasets/datasets_ramien/toy_exp/data'
self.pp_name = os.path.join('mdt', self.label_type, 'train')
self.pp_data_path = os.path.join(pp_root_dir, self.pp_name)
self.pp_test_name = os.path.join('mdt', self.label_type, 'test')
self.pp_test_data_path = os.path.join(pp_root_dir,
self.pp_test_name)
self.select_prototype_subset = None
#########################
# Data Loader #
#########################
# select modalities from preprocessed data
self.channels = [0]
self.n_channels = len(self.channels)
# patch_size to be used for training. pre_crop_size is the patch_size before data augmentation.
self.pre_crop_size_3D = [288, 288, 40]
self.patch_size_3D = [288, 288, 40]
self.patch_size = self.patch_size_3D
self.pre_crop_size = self.pre_crop_size_3D
# ratio of free sampled batch elements before class balancing is triggered
# (>0 to include "empty"/background patches.)
self.batch_sample_slack = 0.2
# set 2D network to operate in 3D images.
self.merge_2D_to_3D_preds = False
# feed +/- n neighbouring slices into channel dimension. set to None for no context.
self.n_3D_context = None
if self.n_3D_context is not None and self.dim == 2:
self.n_channels *= (self.n_3D_context * 2 + 1)
#########################
# Architecture #
#########################
self.start_filts = 48 if self.dim == 2 else 24
self.end_filts = self.start_filts * 4 if self.dim == 2 else self.start_filts * 2
self.res_architecture = 'resnet50' # 'resnet101', 'resnet50'
self.norm = None # one of None, 'instance_norm', 'batch_norm'
# 0 for no weight decay
self.weight_decay = 3e-8
# which weights to exclude from weight decay, options: ["norm", "bias"].
self.exclude_from_wd = ("norm", )
# one of 'xavier_uniform', 'xavier_normal', or 'kaiming_normal', None (= default = 'kaiming_uniform')
self.weight_init = None
#########################
# Schedule / Selection #
#########################
self.num_epochs = 60
self.num_train_batches = 50
self.batch_size = 1
self.do_validation = True
# decide whether to validate on entire patient volumes (like testing) or sampled patches (like training)
# the former is more accurate, while the latter is faster (depending on volume size)
self.val_mode = 'val_sampling' # one of 'val_sampling' , 'val_patient'
if self.val_mode == 'val_patient':
self.max_val_patients = None # if 'None' iterates over entire val_set once.
if self.val_mode == 'val_sampling':
self.num_val_batches = 8
# set dynamic_lr_scheduling to True to apply LR scheduling with below settings.
self.dynamic_lr_scheduling = True
self.lr_decay_factor = 0.7
self.scheduling_patience = np.ceil(
7200 / (self.num_train_batches * self.batch_size))
self.scheduling_criterion = 'all_ap'
self.scheduling_mode = 'min' if "loss" in self.scheduling_criterion else 'max'
#########################
# Testing / Plotting #
#########################
# set the top-n epochs to be saved for temporal averaging in testing.
self.save_n_models = 5
self.test_n_epochs = 5
# set a minimum epoch number for saving in case of instabilities in the first phase of training.
self.min_save_thresh = 0 if self.dim == 2 else 0
self.report_score_level = ['patient', 'rois'
] # choose list from 'patient', 'rois'
self.class_dict = {1: 'all'} # 0 is background.
self.patient_class_of_interest = 1 # patient metrics are only plotted for one class.
self.ap_match_ious = [0.1, 0.5, 0.7, 0.8, 0.9
] # list of ious to be evaluated for ap-scoring.
self.model_selection_criteria = [
'all_ap'
] # criteria to average over for saving epochs.
self.min_det_thresh = 0.1 # minimum confidence value to select predictions for evaluation.
# threshold for clustering predictions together (wcs = weighted cluster scoring).
# needs to be >= the expected overlap of predictions coming from one model (typically NMS threshold).
# if too high, preds of the same object are separate clusters.
self.wcs_iou = 1e-2
self.plot_prediction_histograms = True
self.plot_stat_curves = True
#########################
# Data Augmentation #
#########################
self.da_kwargs = {
'do_elastic_deform':
True,
'alpha': (0., 150.),
'sigma': (10., 30.),
'do_rotation':
False,
'angle_x': (0., 2 * np.pi),
'angle_y': (0., 0),
'angle_z': (0., 0),
'do_scale':
False,
'scale': (0.8, 1.1),
'random_crop':
False,
'rand_crop_dist':
(self.patch_size[0] / 2. - 3, self.patch_size[1] / 2. - 3),
'border_mode_data':
'constant',
'border_cval_data':
0,
'order_data':
1
}
if self.dim == 3:
self.da_kwargs['do_elastic_deform'] = False
self.da_kwargs['angle_x'] = (0, 0.0)
self.da_kwargs['angle_y'] = (0, 0.0) #must be 0!!
self.da_kwargs['angle_z'] = (0., 2 * np.pi)
#########################
# Add model specifics #
#########################
{
'detection_unet': self.add_det_unet_configs,
'mrcnn': self.add_mrcnn_configs,
'ufrcnn': self.add_mrcnn_configs,
'retina_net': self.add_mrcnn_configs,
'retina_unet': self.add_mrcnn_configs,
}[self.model]()
def __init__(self, server_env=None):
#########################
# Preprocessing #
#########################
self.root_dir = '../../../Moscow_NRRD_Output'
# self.root_dir = '/path/to/raw/data'
self.raw_data_dir = '{}/nrrd_file'.format(self.root_dir)
self.pp_dir_preq = '../../../Moscow_NRRD_Full-Numpy'
self.pp_dir = '{}/pp_norm'.format(self.pp_dir_preq)
# self.pp_dir = '{}/pp_norm'.format(self.root_dir)
self.target_spacing = (0.7, 0.7, 1.25)
#########################
# I/O #
#########################
# one out of [2, 3]. dimension the model operates in.
self.dim = 3
# one out of ['mrcnn', 'retina_net', 'retina_unet', 'detection_unet', 'ufrcnn', 'detection_unet'].
self.model = 'retina_net'
# self.model = 'mrcnn'
DefaultConfigs.__init__(self, self.model, server_env, self.dim)
# int [0 < dataset_size]. select n patients from dataset for prototyping. If None, all data is used.
self.select_prototype_subset = None
# path to preprocessed data.
self.pp_name = 'pp_norm'
self.input_df_name = 'info_df.pickle'
self.pp_data_path = '../Moscow_NRRD_Full-Numpy/{}'.format(self.pp_name)
# self.pp_data_path = '/path/to/preprocessed/data/{}'.format(self.pp_name)
self.pp_test_data_path = self.pp_data_path #change if test_data in separate folder.
# settings for deployment in cloud.
if server_env:
# path to preprocessed data.
self.pp_name = 'pp_fg_slices'
self.crop_name = 'pp_fg_slices_packed'
self.pp_data_path = '/path/to/preprocessed/data/{}/{}'.format(
self.pp_name, self.crop_name)
self.pp_test_data_path = self.pp_data_path
self.select_prototype_subset = None
#########################
# Data Loader #
#########################
# select modalities from preprocessed data
self.channels = [0]
self.n_channels = len(self.channels)
# patch_size to be used for training. pre_crop_size is the patch_size before data augmentation.
self.pre_crop_size_2D = [300, 300]
self.patch_size_2D = [288, 288]
self.pre_crop_size_3D = [156, 156, 96]
self.patch_size_3D = [128, 128, 64]
self.patch_size = self.patch_size_2D if self.dim == 2 else self.patch_size_3D
self.pre_crop_size = self.pre_crop_size_2D if self.dim == 2 else self.pre_crop_size_3D
# ratio of free sampled batch elements before class balancing is triggered
# (>0 to include "empty"/background patches.)
self.batch_sample_slack = 0.1
# set 2D network to operate in 3D images.
self.merge_2D_to_3D_preds = True
# feed +/- n neighbouring slices into channel dimension. set to None for no context.
self.n_3D_context = None
if self.n_3D_context is not None and self.dim == 2:
self.n_channels *= (self.n_3D_context * 2 + 1)
#########################
# Architecture #
#########################
self.start_filts = 48 if self.dim == 2 else 18
self.end_filts = self.start_filts * 4 if self.dim == 2 else self.start_filts * 2
self.res_architecture = 'resnet50' # 'resnet101' , 'resnet50'
self.norm = None # one of None, 'instance_norm', 'batch_norm'
self.weight_decay = 0
# one of 'xavier_uniform', 'xavier_normal', or 'kaiming_normal', None (=default = 'kaiming_uniform')
self.weight_init = None
#########################
# Schedule / Selection #
#########################
# self.num_epochs = 150
# self.num_epochs = 2 ##### debug
self.num_epochs = 100
# self.num_epochs = 5
self.num_train_batches = 80
# self.num_train_batches = 1
# self.num_train_batches = 200 if self.dim == 2 else 200
self.batch_size = 32 if self.dim == 2 else 15
# self.batch_size = 2 ##### debug
self.do_validation = True
# decide whether to validate on entire patient volumes (like testing) or sampled patches (like training)
# the former is morge accurate, while the latter is faster (depending on volume size)
self.val_mode = 'val_sampling' # one of 'val_sampling' , 'val_patient'
if self.val_mode == 'val_patient':
# self.max_val_patients = 50
self.max_val_patients = 1
# self.max_val_patients = 2 # if 'None' iterates over entire val_set once.
if self.val_mode == 'val_sampling':
# self.num_val_batches = 50
# self.num_val_batches = 2
self.max_val_patients = 1
#########################
# Testing / Plotting #
#########################
# set the top-n-epochs to be saved for temporal averaging in testing.
self.save_n_models = 5
self.test_n_epochs = 5
# set a minimum epoch number for saving in case of instabilities in the first phase of training.
self.min_save_thresh = 0 if self.dim == 2 else 0
self.report_score_level = ['patient', 'rois'
] # choose list from 'patient', 'rois'
self.class_dict = {1: 'truenod'} # 0 is background.
self.patient_class_of_interest = 1 # patient metrics are only plotted for one class.
self.ap_match_ious = [0.1
] # list of ious to be evaluated for ap-scoring.
self.model_selection_criteria = [
'truenod_ap'
] # criteria to average over for saving epochs.
self.min_det_thresh = 0.1 # minimum confidence value to select predictions for evaluation.
# threshold for clustering predictions together (wcs = weighted cluster scoring).
# needs to be >= the expected overlap of predictions coming from one model (typically NMS threshold).
# if too high, preds of the same object are separate clusters.
self.wcs_iou = 1e-5
self.plot_prediction_histograms = True
self.plot_stat_curves = True
#########################
# Data Augmentation #
#########################
self.da_kwargs = {
'do_elastic_deform':
True,
'alpha': (0., 1500.),
'sigma': (30., 50.),
'do_rotation':
True,
'angle_x': (0., 2 * np.pi),
'angle_y': (0., 0),
'angle_z': (0., 0),
'do_scale':
True,
'scale': (0.8, 1.1),
'random_crop':
False,
'rand_crop_dist':
(self.patch_size[0] / 2. - 3, self.patch_size[1] / 2. - 3),
'border_mode_data':
'constant',
'border_cval_data':
0,
'order_data':
1
}
if self.dim == 3:
self.da_kwargs['do_elastic_deform'] = False
self.da_kwargs['angle_x'] = (0, 0.0)
self.da_kwargs['angle_y'] = (0, 0.0) #must be 0!!
self.da_kwargs['angle_z'] = (0., 2 * np.pi)
#########################
# Add model specifics #
#########################
{
'detection_unet': self.add_det_unet_configs,
'mrcnn': self.add_mrcnn_configs,
'ufrcnn': self.add_mrcnn_configs,
'retina_net': self.add_mrcnn_configs,
'retina_unet': self.add_mrcnn_configs,
}[self.model]()
def __init__(self):
self.gpu = '4'
os.environ['CUDA_VISIBLE_DEVICES'] = self.gpu
#########################
# I/O #
#########################
# one out of [2, 3]. dimension the model operates in.
self.dim = 3
# one out of ['mrcnn', 'seg_mrcnn','retina_net', 'retina_unet', 'detection_unet', 'ufrcnn', 'detection_unet'].
self.model = 'mrcnn'
DefaultConfigs.__init__(self, self.model, self.dim)
# path to preprocessed data.
self.pp_name = 'abus_npy'
self.input_df_name = 'info_df.pickle'
self.input_id_name = 'fold_ids.pickle'
self.pid_pth = 'fold_ids.txt'
self.pp_data_path = '/shenlab/lab_stor6/yuezhou/ABUSdata/{}/'.format(
self.pp_name)
self.pp_test_data_path = self.pp_data_path #change if test_data in separate folder.
#########################
# Data Loader #
#########################
# data aug in training
self.data_aug_training = False
# select modalities from preprocessed data
self.channels = [0]
self.n_channels = len(self.channels)
# patch_size to be used for training. pre_crop_size is the patch_size before data augmentation.
#self.pre_crop_size_2D = [300, 300]
#self.patch_size_2D = [288, 288]
if self.data_aug_training == True:
self.pre_crop_size_3D = [72, 144, 144]
else:
self.pre_crop_size_3D = [64, 128, 128]
self.patch_size_3D = [64, 128, 128] #[128, 128, 64]
self.patch_size = self.patch_size_3D #self.patch_size_2D if self.dim == 2 else self.patch_size_3D
self.pre_crop_size = self.pre_crop_size_3D #self.pre_crop_size_2D if self.dim == 2 else self.pre_crop_size_3D
# ratio of free sampled batch elements before class balancing is triggered
# (>0 to include "empty"/background patches.)
self.batch_sample_slack = 0.5 #0.2
#########################
# Architecture #
#########################
self.backbone_path = 'models/backbone_vnet.py'
self.multi_scale_det = False
self.start_filts = 48 if self.dim == 2 else 18
if 'vnet' in self.backbone_path:
if self.multi_scale_det == False:
self.end_filts = [32, 64, 128, 256, 256]
else:
self.end_filts = [
36, 36, 36, 36, 36
] #self.start_filts * 4 if self.dim == 2 else self.start_filts * 2
if 'fpn' in self.backbone_path:
self.end_filts = [
36, 36, 36, 36, 36
] #self.start_filts * 4 if self.dim == 2 else self.start_filts * 2
self.res_architecture = 'resnet50' # 'resnet101' , 'resnet50'
self.norm = None # one of None, 'instance_norm', 'batch_norm'
self.weight_decay = 0
# one of 'xavier_uniform', 'xavier_normal', or 'kaiming_normal', None (=default = 'kaiming_uniform')
self.weight_init = None
#########################
# Schedule / Selection #
#########################
self.debug = 0
if self.debug == 1:
self.num_epochs = 2
self.num_train_batches = 2 #2 if self.dim == 2 else 2
self.batch_size = 2 #20 if self.dim == 2 else 2
self.n_workers = 1
else:
self.num_epochs = 250
self.num_train_batches = 200 if self.dim == 2 else 200
self.batch_size = 20 if self.dim == 2 else 2
self.n_workers = 16
self.do_validation = True
# decide whether to validate on entire patient volumes (like testing) or sampled patches (like training)
# the former is morge accurate, while the latter is faster (depending on volume size)
self.val_mode = 'val_sampling' # this is a bug only sampling one of 'val_sampling' , 'val_patient'
if self.debug == 1:
self.num_val_batches = 2
else:
self.num_val_batches = None
self.new_data = True
self.text_for_next = False
#########################
# loss #
#########################
# in ['BCE','roiDice','mapDice']
self.mask_loss_flag = 'BCE'
# in ['seg-only','mrcnn-only','frcnn-only','mrcnn-seg','frcnn-seg','mrcnn-seg-fusion']
self.loss_flag = 'mrcnn-seg-fusion'
#########################
# fusion method #
#########################
#fusion in prob or feature
self.fusion_prob_feature = 'prob'
# in ['cat-only','add-only','weight-cat','weight-add']
self.fusion_method = 'weight-add'
# in ['before','after']
self.fusion_feature_method = 'after'
#fusion conoral number
self.fusion_conv_num = 'no' #'no' or 'more' or 'less' or 'one'
#########################
# Testing / Plotting #
#########################
# show detection box score
self.show_det_source_th = 0.1
# patch stride during testing
self.testing_patch_stride = [64, 128, 128]
# set the top-n-epochs to be saved for temporal averaging in testing.
self.save_n_models = 5
self.test_n_epochs = 5
self.testing_epoch_num = 0
# test the best epoch or the last epoch
self.test_last_epoch = False
# show image
if self.debug == 1:
self.show_train_images = 1
self.show_val_images = 1
else:
self.show_train_images = 5
self.show_val_images = 5
#select detected box score
#self.source_th = 0.1
# set a minimum epoch number for saving in case of instabilities in the first phase of training.
self.min_save_thresh = 0 if self.dim == 2 else 0
self.report_score_level = ['patient', 'rois'
] # choose list from 'patient', 'rois'
self.class_dict = {
1: 'mass'
} #{1: 'benign', 2: 'malignant'} # 0 is background.
self.patient_class_of_interest = 1 # patient metrics are only plotted for one class.
self.ap_match_ious = [0.1
] # list of ious to be evaluated for ap-scoring.
#['val_dice_seg','val_dice_mask','val_dice_fusion']#criteria to average over for saving epochs.
if 'seg' in self.loss_flag and 'seg-only' not in self.loss_flag:
self.model_selection_criteria = [
'val_dice_fusion'
] #criteria to average over for saving epochs.
if 'seg-only' in self.loss_flag:
self.model_selection_criteria = ['val_deice_seg']
if 'seg' not in self.loss_flag:
self.model_selection_criteria = ['val_precision', 'val_recall']
self.min_det_thresh = 0.1 # minimum confidence value to select predictions for evaluation.
#########################
# Data Augmentation #
#########################
self.da_kwargs = {
'do_elastic_deform':
True,
'alpha': (0., 1500.),
'sigma': (30., 50.),
'do_rotation':
True,
'angle_x': (0., 2 * np.pi),
'angle_y': (0., 0),
'angle_z': (0., 0),
'do_scale':
True,
'scale': (0.8, 1.1),
'random_crop':
False,
'rand_crop_dist':
(self.patch_size[0] / 2. - 3, self.patch_size[1] / 2. - 3),
'border_mode_data':
'constant',
'border_cval_data':
0,
'order_data':
1
}
if self.dim == 3:
self.da_kwargs['do_elastic_deform'] = False
self.da_kwargs['angle_x'] = (0, 0.0)
self.da_kwargs['angle_y'] = (0, 0.0) #must be 0!!
self.da_kwargs['angle_z'] = (0., 2 * np.pi)
#########################
# Add model specifics #
#########################
{
'detection_unet': self.add_det_unet_configs,
'mrcnn': self.add_mrcnn_configs,
'ufrcnn': self.add_mrcnn_configs,
'retina_net': self.add_mrcnn_configs,
'retina_unet': self.add_mrcnn_configs,
}[self.model]()
def __init__(self, server_env=None):
#########################
# Preprocessing #
#########################
self.root_dir = '/media/gregor/HDD2TB/data/toy_mdt'
#########################
# I/O #
#########################
# one out of [2, 3]. dimension the model operates in.
self.dim = 2
# one out of ['mrcnn', 'retina_net', 'retina_unet', 'detection_unet', 'ufrcnn', 'detection_unet'].
self.model = 'mrcnn'
DefaultConfigs.__init__(self, self.model, server_env, self.dim)
# int [0 < dataset_size]. select n patients from dataset for prototyping.
self.select_prototype_subset = None
self.hold_out_test_set = True
self.n_train_data = 2500
# choose one of the 3 toy experiments described in https://arxiv.org/pdf/1811.08661.pdf
# one of ['donuts_shape', 'donuts_pattern', 'circles_scale'].
toy_mode = 'donuts_shape_nonoise_dia12'
# path to preprocessed data.
self.input_df_name = 'info_df.pickle'
self.pp_name = os.path.join(toy_mode, 'train')
self.pp_data_path = os.path.join(self.root_dir, self.pp_name)
self.pp_test_name = os.path.join(toy_mode, 'test')
self.pp_test_data_path = os.path.join(self.root_dir, self.pp_test_name)
# settings for deployment in cloud.
if server_env:
# path to preprocessed data.
pp_root_dir = '/datasets/datasets_ramien/toy_exp/data'
self.pp_name = os.path.join(toy_mode, 'train')
self.pp_data_path = os.path.join(pp_root_dir, self.pp_name)
self.pp_test_name = os.path.join(toy_mode, 'test')
self.pp_test_data_path = os.path.join(pp_root_dir,
self.pp_test_name)
self.select_prototype_subset = None
#########################
# Data Loader #
#########################
# select modalities from preprocessed data
self.channels = [0]
self.n_channels = len(self.channels)
# patch_size to be used for training. pre_crop_size is the patch_size before data augmentation.
self.pre_crop_size_2D = [320, 320]
self.patch_size_2D = [320, 320]
self.patch_size = self.patch_size_2D if self.dim == 2 else self.patch_size_3D
self.pre_crop_size = self.pre_crop_size_2D if self.dim == 2 else self.pre_crop_size_3D
# ratio of free sampled batch elements before class balancing is triggered
# (>0 to include "empty"/background patches.)
self.batch_sample_slack = 0.2
# set 2D network to operate in 3D images.
self.merge_2D_to_3D_preds = False
# feed +/- n neighbouring slices into channel dimension. set to None for no context.
self.n_3D_context = None
if self.n_3D_context is not None and self.dim == 2:
self.n_channels *= (self.n_3D_context * 2 + 1)
#########################
# Architecture #
#########################
self.start_filts = 48 if self.dim == 2 else 18
self.end_filts = self.start_filts * 4 if self.dim == 2 else self.start_filts * 2
self.res_architecture = 'resnet50' # 'resnet101' , 'resnet50'
self.norm = None # one of None, 'instance_norm', 'batch_norm'
self.weight_decay = 0
# one of 'xavier_uniform', 'xavier_normal', or 'kaiming_normal', None (=default = 'kaiming_uniform')
self.weight_init = None
#########################
# Schedule / Selection #
#########################
self.num_epochs = 24
self.num_train_batches = 100 if self.dim == 2 else 200
self.batch_size = 20 if self.dim == 2 else 8
self.do_validation = True
# decide whether to validate on entire patient volumes (like testing) or sampled patches (like training)
# the former is morge accurate, while the latter is faster (depending on volume size)
self.val_mode = 'val_patient' # one of 'val_sampling' , 'val_patient'
if self.val_mode == 'val_patient':
self.max_val_patients = None # if 'None' iterates over entire val_set once.
if self.val_mode == 'val_sampling':
self.num_val_batches = 50
#########################
# Testing / Plotting #
#########################
# set the top-n-epochs to be saved for temporal averaging in testing.
self.save_n_models = 5
self.test_n_epochs = 5
# set a minimum epoch number for saving in case of instabilities in the first phase of training.
self.min_save_thresh = 0 if self.dim == 2 else 0
self.report_score_level = ['patient', 'rois'
] # choose list from 'patient', 'rois'
self.class_dict = {1: 'benign', 2: 'malignant'} # 0 is background.
self.patient_class_of_interest = 2 # patient metrics are only plotted for one class.
self.ap_match_ious = [0.1
] # list of ious to be evaluated for ap-scoring.
self.model_selection_criteria = [
'benign_ap', 'malignant_ap'
] # criteria to average over for saving epochs.
self.min_det_thresh = 0.1 # minimum confidence value to select predictions for evaluation.
# threshold for clustering predictions together (wcs = weighted cluster scoring).
# needs to be >= the expected overlap of predictions coming from one model (typically NMS threshold).
# if too high, preds of the same object are separate clusters.
self.wcs_iou = 1e-5
self.plot_prediction_histograms = True
self.plot_stat_curves = False
#########################
# Data Augmentation #
#########################
self.da_kwargs = {
'do_elastic_deform':
True,
'alpha': (0., 1500.),
'sigma': (30., 50.),
'do_rotation':
True,
'angle_x': (0., 2 * np.pi),
'angle_y': (0., 0),
'angle_z': (0., 0),
'do_scale':
True,
'scale': (0.8, 1.1),
'random_crop':
False,
'rand_crop_dist':
(self.patch_size[0] / 2. - 3, self.patch_size[1] / 2. - 3),
'border_mode_data':
'constant',
'border_cval_data':
0,
'order_data':
1
}
if self.dim == 3:
self.da_kwargs['do_elastic_deform'] = False
self.da_kwargs['angle_x'] = (0, 0.0)
self.da_kwargs['angle_y'] = (0, 0.0) #must be 0!!
self.da_kwargs['angle_z'] = (0., 2 * np.pi)
#########################
# Add model specifics #
#########################
{
'detection_unet': self.add_det_unet_configs,
'mrcnn': self.add_mrcnn_configs,
'ufrcnn': self.add_mrcnn_configs,
'ufrcnn_surrounding': self.add_mrcnn_configs,
'retina_net': self.add_mrcnn_configs,
'retina_unet': self.add_mrcnn_configs,
'prob_detector': self.add_mrcnn_configs,
}[self.model]()
def __init__(self, server_env=False):
#Change some things if debugging
#Set always to false, it is set to true by others
self.debugging = False
#########################
# Preprocessing #
#########################
#Already done!
self.root_dir = r'../'
#self.raw_data_dir = os.path.join(self.root_dir, './')
self.pp_dir = os.path.join(self.root_dir, 'out')
self.target_spacing = (0.5, 0.5, 3.)
#########################
# I/O #
#########################
# one out of [2, 3]. dimension the model operates in.
self.dim = 3
# one out of ['mrcnn', 'retina_net', 'retina_unet', 'detection_unet', 'ufrcnn'].
# Only retina_unet can be used with the current model setup
self.model = 'retina_unet'
self.model_path = '././'
DefaultConfigs.__init__(self, self.model, server_env, self.dim)
# int [0 < dataset_size]. select n patients from dataset for prototyping. If None, all data is used.
self.select_prototype_subset = None
# path to preprocessed data.
self.pp_name = 'out'
self.input_df_name = 'info_df.pickle'
self.pp_data_path = os.path.join(self.root_dir, self.pp_name)
self.pp_test_data_path = self.pp_data_path #change if test_data in separate folder.
# settings for deployment in cloud.
if server_env:
# path to preprocessed data.
self.pp_name = ''
self.crop_name = ''
self.pp_data_path = ''
self.pp_test_data_path = self.pp_data_path
self.select_prototype_subset = None
#########################
# Data Loader #
#########################
#Use a single CV split
self.n_cv_splits = 5
# select modalities from preprocessed data
self.channels = list(range(8))
self.n_channels = len(self.channels)
# patch_size to be used for training. pre_crop_size is the patch_size before data augmentation.
self.pre_crop_size_2D = [160, 160]
self.patch_size_2D = [160, 160]
self.pre_crop_size_3D = [160, 160, 24]
self.patch_size_3D = [160, 160, 24]
self.patch_size = self.patch_size_2D if self.dim == 2 else self.patch_size_3D
self.pre_crop_size = self.pre_crop_size_2D if self.dim == 2 else self.pre_crop_size_3D
# ratio of free sampled batch elements before class balancing is triggered
# (>0 to include "empty"/background patches.)
self.batch_sample_slack = 0.2
# set 2D network to operate in 3D images.
self.merge_2D_to_3D_preds = self.dim == 2
# feed +/- n neighbouring slices into channel dimension. set to None for no context.
self.n_3D_context = 3
if self.n_3D_context is not None and self.dim == 2:
self.n_channels *= (self.n_3D_context * 2 + 1)
#########################
# Architecture #
#########################
self.start_filts = 48 if self.dim == 2 else 15
self.end_filts = self.start_filts * 4 if self.dim == 2 else self.start_filts * 2
self.n_blocks = [3, 7, 21, 3] #[3, 4, 23, 3] 'resnet101'
self.norm = 'batch_norm' # one of None, 'instance_norm', 'batch_norm'
# 0 for no weight decay
self.weight_decay = 0
# one of 'xavier_uniform', 'xavier_normal', or 'kaiming_normal', None (=default = 'kaiming_uniform')
self.weight_init = None
#########################
# Schedule / Selection #
#########################
self.num_epochs = 115 #99
self.num_train_batches = 120 if self.dim == 2 else 120
self.batch_size = 20 if self.dim == 2 else 6
self.do_validation = True
# decide whether to validate on entire patient volumes (like testing) or sampled patches (like training)
# the former is more accurate, while the latter is faster (depending on volume size)
self.val_mode = 'val_sampling' # one of 'val_sampling' , 'val_patient'
if self.val_mode == 'val_patient':
self.max_val_patients = 50 # if 'None' iterates over entire val_set once.
if self.val_mode == 'val_sampling':
self.num_val_batches = 50
self.optimizer = "Adam"
# set dynamic_lr_scheduling to True to apply LR scheduling with below settings.
self.dynamic_lr_scheduling = False
self.lr_decay_factor = 0.25
self.scheduling_patience = np.ceil(
16000 / (self.num_train_batches * self.batch_size))
self.scheduling_criterion = 'malignant_ap'
self.scheduling_mode = 'min' if "loss" in self.scheduling_criterion else 'max'
#########################
# Testing / Plotting #
#########################
# General matching IOU
self.match_iou = 1e-5
# set the top-n-epochs to be saved for temporal averaging in testing.
self.save_n_models = 5
self.test_n_epochs = 5
# If true, all epochs (not only best k) are kept
self.keep_all_epochs = False
# use 'train', 'val' or 'test' data for testing
self.test_subset = 'test'
# Drop some channels during test?
#T2:[0], B500,B800+,ADC:[1,2,3], ktrans:[4], Perf:[5,6,7]
self.drop_channels_test = []
# use a temporal ensemble of a list of epochs, or None, to use instead the best validation cps
def steps(start, end, n):
if n < 2: raise Exception("Behaviour not defined for n<2")
step = (end - start) / float(n - 1)
return [int(round(start + x * step)) for x in range(n)]
self.test_checkpoints = None #steps(25, self.num_epochs, self.test_n_epochs)
# set a minimum epoch number for saving in case of instabilities in the first phase of training.
self.min_save_thresh = 0 if self.dim == 2 else 0
self.scan_det_thresh = False #Used in evaluator > return_metrics
self.report_score_level = ['patient', 'rois'
] # choose list from 'patient', 'rois'
self.class_dict = {
1: 'benign',
2: 'GGG_1',
3: 'GGG_2',
4: 'GGG_3'
} # 0 is background.
self.patient_class_of_interest = 3 # patient metrics are only plotted for one class.
self.ap_match_ious = [self.match_iou
] # list of ious to be evaluated for ap-scoring.
# criteria to average over for saving epochs.
self.model_selection_criteria = [
'GGG_%d_%s' % (g, metric) for g in range(1, 4)
for metric in ['ap']
] + ['benign_ap']
self.min_det_thresh = 0. # minimum confidence value to select predictions for evaluation.
#Use prostatex test set too with masked classification loss?
self.use_prostatex_test = True
# evaluates average precision per image and averages over images. instead computing one ap over data set.
self.per_patient_ap = False
# threshold for clustering 2D box predictions to 3D Cubes. Overlap is computed in XY.
self.merge_3D_iou = self.match_iou
#Custom dict preprocessing function to transform classes 10,1 -> 0, 2,3,4,5 -> 1, 20 -> 20
#Please note that class 20 is a very special class for which bce loss is masked!
#correspondance_dict= {0:0, 10:0, 1:0, 2:1, 3:1, 4:1, 5:1, 20:20}
correspondance_dict = {
0: 0,
10: 0,
1: 1,
2: 2,
3: 3,
4: 3,
5: 3,
20: 20
}
def modify_class_target(class_targets):
return [correspondance_dict[target] for target in class_targets]
self.modify_class_target_fn = modify_class_target
# threshold for clustering predictions together (wcs = weighted cluster scoring).
# needs to be >= the expected overlap of predictions coming from one model (typically NMS threshold).
# if too high, preds of the same object are separate clusters.
self.wcs_iou = 1e-5
self.plot_prediction_histograms = False
self.plot_stat_curves = False
# if True, test data lies in a separate folder and is not part of the cross validation.
self.hold_out_test_set = True
# if hold_out_test_set provided, ensemble predictions over models of all trained cv-folds.
# implications for hold-out test sets: if True, evaluate folds separately on the test set, aggregate only the
# evaluations. if False, aggregate the raw predictions across all folds, then evaluate.
self.ensemble_folds = True
#########################
# Data Augmentation #
#########################
self.da_kwargs = {
'do_elastic_deform':
True,
'alpha': (0., 300.),
'sigma': (20., 40.),
'do_rotation':
True,
'angle_x': (-np.pi / 30., np.pi / 30),
'angle_y': (-np.pi / 20., np.pi / 20) if self.dim == 2 else
(0., 0.), #must be 0!!
'angle_z': (-np.pi / 20., np.pi / 20),
'do_scale':
True,
'scale': (1 / 1.15, 1.15),
'random_crop':
False,
'rand_crop_dist':
(self.patch_size[0] / 2. - 3, self.patch_size[1] / 2. - 3),
'border_mode_data':
'constant',
'border_cval_data':
0,
'order_data':
3
}
self.test_aug = False #Seems to be true by default
self.mirror_axes = (1, )
#Custom augmentation: drop a channel with some prob
#Do not drop T2 nor final channels & consider perfusion channels as one
# 0:T2, 1:B500, 2:B800, 3:ADC, 4:ktrans,
# 5:Prostate mask, 6:CZ mask, 7: PZ mask
self.droppable_channels = [[1], [2], [3], [4]]
self.channel_drop_p = 0.05
#########################
# Add model specifics #
#########################
{
'detection_unet': self.add_det_unet_configs,
'mrcnn': self.add_mrcnn_configs,
'ufrcnn': self.add_mrcnn_configs,
'retina_net': self.add_mrcnn_configs,
'retina_unet': self.add_mrcnn_configs,
'retina_unet_coral': self.add_mrcnn_configs,
}[self.model]()
def __init__(self, server_env=None):
#########################
# Preprocessing #
#########################
self.root_dir = '/home/gregor/datasets/toy_mdt'
#########################
# I/O #
#########################
# one out of [2, 3]. dimension the model operates in.
self.dim = 2
DefaultConfigs.__init__(self, server_env, self.dim)
# one out of ['mrcnn', 'retina_net', 'retina_unet', 'detection_unet', 'ufrcnn'].
self.model = 'mrcnn'
self.model_path = 'models/{}.py'.format(self.model if not 'retina' in self.model else 'retina_net')
self.model_path = os.path.join(self.source_dir, self.model_path)
# int [0 < dataset_size]. select n patients from dataset for prototyping.
self.select_prototype_subset = None
self.hold_out_test_set = True
# including val set. will be 3/4 train, 1/4 val.
self.n_train_val_data = 2500
# choose one of the 3 toy experiments described in https://arxiv.org/pdf/1811.08661.pdf
# one of ['donuts_shape', 'donuts_pattern', 'circles_scale'].
toy_mode = 'donuts_shape_noise'
# path to preprocessed data.
self.info_df_name = 'info_df.pickle'
self.pp_name = os.path.join(toy_mode, 'train')
self.data_sourcedir = os.path.join(self.root_dir, self.pp_name)
self.pp_test_name = os.path.join(toy_mode, 'test')
self.test_data_sourcedir = os.path.join(self.root_dir, self.pp_test_name)
# settings for deployment in cloud.
if server_env:
# path to preprocessed data.
pp_root_dir = '/datasets/datasets_ramien/toy_exp/data'
self.pp_name = os.path.join(toy_mode, 'train')
self.data_sourcedir = os.path.join(pp_root_dir, self.pp_name)
self.pp_test_name = os.path.join(toy_mode, 'test')
self.test_data_sourcedir = os.path.join(pp_root_dir, self.pp_test_name)
self.select_prototype_subset = None
#########################
# Data Loader #
#########################
# select modalities from preprocessed data
self.channels = [0]
self.n_channels = len(self.channels)
self.plot_bg_chan = 0
# patch_size to be used for training. pre_crop_size is the patch_size before data augmentation.
self.pre_crop_size_2D = [320, 320]
self.patch_size_2D = [320, 320]
self.patch_size = self.patch_size_2D if self.dim == 2 else self.patch_size_3D
self.pre_crop_size = self.pre_crop_size_2D if self.dim == 2 else self.pre_crop_size_3D
# ratio of free sampled batch elements before class balancing is triggered
# (>0 to include "empty"/background patches.)
self.batch_random_ratio = 0.2
# set 2D network to operate in 3D images.
self.merge_2D_to_3D_preds = False
#########################
# Architecture #
#########################
self.start_filts = 48 if self.dim == 2 else 18
self.end_filts = self.start_filts * 4 if self.dim == 2 else self.start_filts * 2
self.res_architecture = 'resnet50' # 'resnet101' , 'resnet50'
self.norm = "instance_norm" # one of None, 'instance_norm', 'batch_norm'
# one of 'xavier_uniform', 'xavier_normal', or 'kaiming_normal', None (=default = 'kaiming_uniform')
self.weight_init = "xavier_uniform"
# compatibility
self.regression_n_features = 1
self.num_classes = 2 # excluding bg
self.num_seg_classes = 3 # incl bg
#########################
# Schedule / Selection #
#########################
self.num_epochs = 26
self.num_train_batches = 100 if self.dim == 2 else 200
self.batch_size = 20 if self.dim == 2 else 8
self.do_validation = True
# decide whether to validate on entire patient volumes (like testing) or sampled patches (like training)
# the former is morge accurate, while the latter is faster (depending on volume size)
self.val_mode = 'val_patient' # one of 'val_sampling' , 'val_patient'
if self.val_mode == 'val_patient':
self.max_val_patients = "all" # if 'None' iterates over entire val_set once.
if self.val_mode == 'val_sampling':
self.num_val_batches = 50
self.optimizer = "ADAMW"
# set dynamic_lr_scheduling to True to apply LR scheduling with below settings.
self.dynamic_lr_scheduling = True
self.lr_decay_factor = 0.25
self.scheduling_patience = np.ceil(4800 / (self.num_train_batches * self.batch_size))
self.scheduling_criterion = 'donuts_ap'
self.scheduling_mode = 'min' if "loss" in self.scheduling_criterion else 'max'
self.weight_decay = 1e-5
self.exclude_from_wd = ["norm"]
self.clip_norm = 200
#########################
# Testing / Plotting #
#########################
self.ensemble_folds = False
# set the top-n-epochs to be saved for temporal averaging in testing.
self.save_n_models = 5
self.test_n_epochs = 5
self.test_aug_axes = (0, 1, (0, 1))
self.n_test_plots = 2
self.clustering = "wbc"
self.clustering_iou = 1e-5
# set a minimum epoch number for saving in case of instabilities in the first phase of training.
self.min_save_thresh = 0 if self.dim == 2 else 0
self.report_score_level = ['patient', 'rois'] # choose list from 'patient', 'rois'
self.class_labels = [Label(0, 'bg', (*self.white, 0.)),
Label(1, 'circles', (*self.orange, .9)),
Label(2, 'donuts', (*self.blue, .9)),]
if self.class_specific_seg:
self.seg_labels = self.class_labels
self.box_type2label = {label.name: label for label in self.box_labels}
self.class_id2label = {label.id: label for label in self.class_labels}
self.class_dict = {label.id: label.name for label in self.class_labels if label.id != 0}
self.seg_id2label = {label.id: label for label in self.seg_labels}
self.cmap = {label.id: label.color for label in self.seg_labels}
self.metrics = ["ap", "auc", "dice"]
self.patient_class_of_interest = 2 # patient metrics are only plotted for one class.
self.ap_match_ious = [0.1] # list of ious to be evaluated for ap-scoring.
self.model_selection_criteria = {name + "_ap": 1. for name in self.class_dict.values()}# criteria to average over for saving epochs.
self.min_det_thresh = 0.1 # minimum confidence value to select predictions for evaluation.
self.plot_prediction_histograms = True
self.plot_stat_curves = False
self.plot_class_ids = True
#########################
# Data Augmentation #
#########################
self.do_aug = False
self.da_kwargs={
'do_elastic_deform': True,
'alpha':(0., 1500.),
'sigma':(30., 50.),
'do_rotation':True,
'angle_x': (0., 2 * np.pi),
'angle_y': (0., 0),
'angle_z': (0., 0),
'do_scale': True,
'scale':(0.8, 1.1),
'random_crop':False,
'rand_crop_dist': (self.patch_size[0] / 2. - 3, self.patch_size[1] / 2. - 3),
'border_mode_data': 'constant',
'border_cval_data': 0,
'order_data': 1
}
if self.dim == 3:
self.da_kwargs['do_elastic_deform'] = False
self.da_kwargs['angle_x'] = (0, 0.0)
self.da_kwargs['angle_y'] = (0, 0.0) #must be 0!!
self.da_kwargs['angle_z'] = (0., 2 * np.pi)
#########################
# Add model specifics #
#########################
{'detection_fpn': self.add_det_fpn_configs,
'mrcnn': self.add_mrcnn_configs,
'retina_net': self.add_mrcnn_configs,
'retina_unet': self.add_mrcnn_configs,
}[self.model]()
def __init__(self, server_env=False):
#########################
# Predictions #
#########################
self.patient_path = None
self.output_dir = None
#########################
# Preprocessing #
#########################
datasets_dir = os.getenv('MDT_DATASETS_DIR')
self.root_dir = os.path.join(datasets_dir, 'MDT-LIDC-IDRI')
self.raw_data_dir = f'{self.root_dir}/NRRDs'
self.pp_dir = os.path.join(datasets_dir, 'MDT-PP')
self.target_spacing = (0.7, 0.7, 1.25)
#########################
# I/O #
#########################
# one out of [2, 3]. dimension the model operates in.
self.dim = 3
# one out of ['mrcnn', 'retina_net', 'retina_unet', 'detection_unet', 'ufrcnn'].
self.model = 'retina_unet'
DefaultConfigs.__init__(self, self.model, server_env, self.dim)
# int [0 < dataset_size]. select n patients from dataset for prototyping. If None, all data is used.
self.select_prototype_subset = None
# path to preprocessed data.
self.pp_name = 'lidc_mdt'
self.input_df_name = 'info_df.pickle'
self.pp_data_path = self.pp_dir
self.pp_test_data_path = self.pp_data_path #change if test_data in separate folder.
# settings for deployment in cloud.
if server_env:
# path to preprocessed data.
self.pp_name = 'lidc_mdt_npz'
self.crop_name = 'pp_fg_slices_packed'
self.pp_data_path = '/datasets/datasets_ramien/lidc_exp/data/{}'.format(
self.pp_name)
self.pp_test_data_path = self.pp_data_path
self.select_prototype_subset = None
#########################
# Data Loader #
#########################
self.gan_dataset = False
self.train_set_proportion = 1.0
self.n_cv_splits = 10 # 10 to split data 80 train - 10 val - 10 test
# select modalities from preprocessed data
self.channels = [0]
self.n_channels = len(self.channels)
# patch_size to be used for training. pre_crop_size is the patch_size before data augmentation.
self.pre_crop_size_2D = [300, 300]
self.patch_size_2D = [288, 288]
self.pre_crop_size_3D = [156, 156, 96]
self.patch_size_3D = [128, 128, 64]
self.patch_size = self.patch_size_2D if self.dim == 2 else self.patch_size_3D
self.pre_crop_size = self.pre_crop_size_2D if self.dim == 2 else self.pre_crop_size_3D
# ratio of free sampled batch elements before class balancing is triggered
# (>0 to include "empty"/background patches.)
self.batch_sample_slack = 0.2
# set 2D network to operate in 3D images.
self.merge_2D_to_3D_preds = self.dim == 2
# feed +/- n neighbouring slices into channel dimension. set to None for no context.
self.n_3D_context = None
if self.n_3D_context is not None and self.dim == 2:
self.n_channels *= (self.n_3D_context * 2 + 1)
#########################
# Architecture #
#########################
self.start_filts = 48 if self.dim == 2 else 18
self.end_filts = self.start_filts * 4 if self.dim == 2 else self.start_filts * 2
self.res_architecture = 'resnet50' # 'resnet101' , 'resnet50'
self.norm = None # one of None, 'instance_norm', 'batch_norm'
# 0 for no weight decay
self.weight_decay = 0
# one of 'xavier_uniform', 'xavier_normal', or 'kaiming_normal', None (=default = 'kaiming_uniform')
self.weight_init = None
#########################
# Schedule / Selection #
#########################
self.num_epochs = 50
self.num_train_batches = 200 if self.dim == 2 else 200
self.batch_size = 20 if self.dim == 2 else 10
self.do_validation = True
# decide whether to validate on entire patient volumes (like testing) or sampled patches (like training)
# the former is more accurate, while the latter is faster (depending on volume size)
self.val_mode = 'val_sampling' # one of 'val_sampling' , 'val_patient'
if self.val_mode == 'val_patient':
self.max_val_patients = 50 # if 'None' iterates over entire val_set once.
if self.val_mode == 'val_sampling':
self.num_val_batches = 25
self.optimizer = "Adam"
# set dynamic_lr_scheduling to True to apply LR scheduling with below settings.
self.dynamic_lr_scheduling = False
self.lr_decay_factor = 0.25
self.scheduling_patience = np.ceil(
16000 / (self.num_train_batches * self.batch_size))
self.scheduling_criterion = 'malignant_ap'
self.scheduling_mode = 'min' if "loss" in self.scheduling_criterion else 'max'
#########################
# Testing / Plotting #
#########################
# set the top-n-epochs to be saved for temporal averaging in testing.
self.save_n_models = 5
self.test_n_epochs = 5
# set a minimum epoch number for saving in case of instabilities in the first phase of training.
self.min_save_thresh = 0 if self.dim == 2 else 0
self.report_score_level = ['patient', 'rois'
] # choose list from 'patient', 'rois'
#self.class_dict = {1: 'benign', 2: 'malignant'} # 0 is background.
#self.patient_class_of_interest = 2 # patient metrics are only plotted for one class.
self.class_dict = {1: 'nodule'} # 1 output class
self.patient_class_of_interest = 1
self.ap_match_ious = [0.1
] # list of ious to be evaluated for ap-scoring.
self.model_selection_criteria = [
'nodule_ap'
] # ['malignant_ap', 'benign_ap'] # criteria to average over for saving epochs.
self.min_det_thresh = 0.1 # minimum confidence value to select predictions for evaluation.
# threshold for clustering predictions together (wcs = weighted cluster scoring).
# needs to be >= the expected overlap of predictions coming from one model (typically NMS threshold).
# if too high, preds of the same object are separate clusters.
self.wcs_iou = 1e-5
self.plot_prediction_histograms = True
self.plot_stat_curves = True
#########################
# Data Augmentation #
#########################
self.da_kwargs = {
'do_elastic_deform':
True,
'alpha': (0., 1500.),
'sigma': (30., 50.),
'do_rotation':
True,
'angle_x': (0., 2 * np.pi),
'angle_y': (0., 0),
'angle_z': (0., 0),
'do_scale':
True,
'scale': (0.8, 1.1),
'random_crop':
False,
'rand_crop_dist':
(self.patch_size[0] / 2. - 3, self.patch_size[1] / 2. - 3),
'border_mode_data':
'constant',
'border_cval_data':
0,
'order_data':
1
}
if self.dim == 3:
self.da_kwargs['do_elastic_deform'] = False
self.da_kwargs['angle_x'] = (0, 0.0)
self.da_kwargs['angle_y'] = (0, 0.0) #must be 0!!
self.da_kwargs['angle_z'] = (0., 2 * np.pi)
#########################
# Add model specifics #
#########################
{
'detection_unet': self.add_det_unet_configs,
'mrcnn': self.add_mrcnn_configs,
'ufrcnn': self.add_mrcnn_configs,
'retina_net': self.add_mrcnn_configs,
'retina_unet': self.add_mrcnn_configs,
}[self.model]()
def __init__(self, server_env=None):
#########################
# Preprocessing #
#########################
self.root_dir = '/path/to/raw/data'
self.raw_data_dir = '{}/data_nrrd'.format(self.root_dir)
self.pp_dir = '{}/pp_norm'.format(self.root_dir)
self.target_spacing = (0.7, 0.7, 1.25)
#########################
# I/O #
#########################
# one out of [2, 3]. dimension the model operates in.
self.dim = 3
# one out of ['mrcnn', 'retina_net', 'retina_unet', 'generic_unet', 'ufrcnn', 'probabilistic_unet'].
self.model = 'generic_unet'
DefaultConfigs.__init__(self, self.model, server_env, self.dim)
# int [0 < dataset_size]. select n patients from dataset for prototyping. If None, all data is used.
self.select_prototype_subset = None
# path to preprocessing data.
self.pp_name = 'pp_norm'
self.input_df_name = 'info_df.pickle'
self.pp_data_path = '/path/to/preprocessing/data/{}'.format(
self.pp_name)
self.pp_test_data_path = self.pp_data_path #change if test_data in separate folder.
# settings for deployment in cloud.
if server_env:
# path to preprocessing data.
self.pp_name = 'pp_fg_slices'
self.crop_name = 'pp_fg_slices_packed'
self.pp_data_path = '/path/to/preprocessing/data/{}/{}'.format(
self.pp_name, self.crop_name)
self.pp_test_data_path = self.pp_data_path
self.select_prototype_subset = None
#########################
# Data Loader #
#########################
# select modalities from preprocessing data
self.channels = [0]
self.n_channels = len(self.channels)
# patch_size to be used for training. pre_crop_size is the patch_size before data augmentation.
self.pre_crop_size_2D = [300, 300]
self.patch_size_2D = [288, 288]
self.pre_crop_size_3D = [156, 156, 96]
self.patch_size_3D = [128, 128, 64]
self.patch_size = self.patch_size_2D if self.dim == 2 else self.patch_size_3D
self.pre_crop_size = self.pre_crop_size_2D if self.dim == 2 else self.pre_crop_size_3D
# ratio of free sampled batch elements before class balancing is triggered
# (>0 to include "empty"/background patches.)
self.batch_sample_slack = 0.2
# set 2D net to operate in 3D images.
self.merge_2D_to_3D_preds = True
# feed +/- n neighbouring slices into channel dimension. set to None for no context.
self.n_3D_context = None
if self.n_3D_context is not None and self.dim == 2:
self.n_channels *= (self.n_3D_context * 2 + 1)
#########################
# Data Analysis #
#########################
# be set to background if the volume is less than X times of the minimum volume of
# that class in the training data
self.MIN_SIZE_PER_CLASS_FACTOR = 0.5
self.TARGET_SPACING_PERCENTILE = 50
self.FEATUREMAP_MIN_EDGE_LENGTH_BOTTLENECK = 4
self.FEATUREMAP_MIN_EDGE_LENGTH_BOTTLENECK2 = 6
# z is defined as the axis with the highest spacing, also used to
# determine whether to use 2d or 3d data augmentation
self.RESAMPLING_SEPARATE_Z_ANISOTROPY_THRESHOLD = 3
# 1/4 of a patient
self.HOW_MUCH_OF_A_PATIENT_MUST_THE_NETWORK_SEE_AT_STAGE0 = 4
# all samples in the batch cannot cover more than 5% of the entire dataset
self.batch_size_covers_max_percent_of_dataset = 0.05
# minimum batch size >= 2
self.dataset_min_batch_size_cap = 2
#########################
# Architecture #
#########################
self.start_filts = 48 if self.dim == 2 else 18
self.end_filts = self.start_filts * 4 if self.dim == 2 else self.start_filts * 2
self.res_architecture = 'resnet50' # 'resnet101' , 'resnet50'
self.norm = None # one of None, 'instance_norm', 'batch_norm'
self.weight_decay = 0
# one of 'xavier_uniform', 'xavier_normal', or 'kaiming_normal', None (=default = 'kaiming_uniform')
self.weight_init = None
#########################
# Schedule / Selection #
#########################
self.num_epochs = 100
self.num_train_batches = 200 if self.dim == 2 else 200
self.batch_size = 20 if self.dim == 2 else 8
self.do_validation = True
# decide whether to validate on entire patient volumes (like testing) or sampled patches (like training)
# the former is morge accurate, while the latter is faster (depending on volume size)
self.val_mode = 'val_sampling' # one of 'val_sampling' , 'val_patient'
if self.val_mode == 'val_patient':
self.max_val_patients = 50 # if 'None' iterates over entire val_set once.
if self.val_mode == 'val_sampling':
self.num_val_batches = 50
#########################
# Testing / Plotting #
#########################
# set the top-n-epochs to be saved for temporal averaging in testing.
self.save_n_models = 5
self.test_n_epochs = 5
# set a minimum epoch number for saving in case of instabilities in the first phase of training.
self.min_save_thresh = 0 if self.dim == 2 else 0
self.report_score_level = ['patient', 'rois'
] # choose list from 'patient', 'rois'
self.class_dict = {1: 'benign', 2: 'malignant'} # 0 is background.
self.patient_class_of_interest = 2 # patient metrics are only plotted for one class.
self.ap_match_ious = [0.1
] # list of ious to be evaluated for ap-scoring.
self.model_selection_criteria = [
'malignant_ap', 'benign_ap'
] # criteria to average over for saving epochs.
self.min_det_thresh = 0.1 # minimum confidence value to select predictions for evaluation.
# threshold of wcs (weighted cluster scoring), used for clustering predictions together.
# needs to be >= the expected overlap of predictions coming from one model.(typically NMS threshold).
self.wcs_iou = 1e-5
self.plot_prediction_histograms = True
self.plot_stat_curves = False
#########################
# Data Augmentation #
#########################
self.da_kwargs = {
'do_elastic_deform':
True,
'alpha': (0., 1500.),
'sigma': (30., 50.),
'do_rotation':
True,
'angle_x': (0., 2 * np.pi),
'angle_y': (0., 0),
'angle_z': (0., 0),
'do_scale':
True,
'scale': (0.8, 1.1),
'random_crop':
False,
'rand_crop_dist':
(self.patch_size[0] / 2. - 3, self.patch_size[1] / 2. - 3),
'border_mode_data':
'constant',
'border_cval_data':
0,
'order_data':
1
}
if self.dim == 3:
self.da_kwargs['do_elastic_deform'] = False
self.da_kwargs['angle_x'] = (0, 0.0)
self.da_kwargs['angle_y'] = (0, 0.0) #must be 0!!
self.da_kwargs['angle_z'] = (0., 2 * np.pi)
self.aug_3D_kwargs = {
"selected_data_channels": None,
"selected_seg_channels": None,
"do_elastic": True,
"elastic_deform_alpha": (0., 900.),
"elastic_deform_sigma": (9., 13.),
"do_scaling": True,
"scale_range": (0.85, 1.25),
"do_rotation": True,
"rotation_x": (-15. / 360 * 2. * np.pi, 15. / 360 * 2. * np.pi),
"rotation_y": (-15. / 360 * 2. * np.pi, 15. / 360 * 2. * np.pi),
"rotation_z": (-15. / 360 * 2. * np.pi, 15. / 360 * 2. * np.pi),
"random_crop": False,
"random_crop_dist_to_border": None,
"do_gamma": True,
"gamma_retain_stats": True,
"gamma_range": (0.7, 1.5),
"p_gamma": 0.3,
"num_threads": 12,
"num_cached_per_thread": 1,
"mirror": True,
"mirror_axes": (0, 1, 2),
"p_eldef": 0.2,
"p_scale": 0.2,
"p_rot": 0.2,
"dummy_2D": False,
"mask_was_used_for_normalization": False,
"all_segmentation_labels": None, # used for pyramid
"move_last_seg_chanel_to_data": False, # used for pyramid
"border_mode_data": "constant",
"advanced_pyramid_augmentations": False # used for pyramid
}
self.aug_2D_kwargs = deepcopy(self.aug_3D_kwargs)
self.aug_2D_kwargs["elastic_deform_alpha"] = (0., 200.)
self.aug_2D_kwargs["elastic_deform_sigma"] = (9., 13.)
self.aug_2D_kwargs["rotation_x"] = (-180. / 360 * 2. * np.pi,
180. / 360 * 2. * np.pi)
# according to unsupported 3d data augmentation, transfer 3d data into 2d data and
# transform them back after augmentation
self.aug_2D_kwargs["dummy_2D"] = False
self.aug_2D_kwargs["mirror_axes"] = (
0, 1) # this can be (0, 1, 2) if dummy_2D=True
#########################
# Add model specifics #
#########################
{
'generic_unet': self.add_gen_unet_configs,
'mrcnn': self.add_mrcnn_configs,
'ufrcnn': self.add_mrcnn_configs,
'retina_net': self.add_mrcnn_configs,
'retina_unet': self.add_mrcnn_configs,
}[self.model]()
def __init__(self, server_env=None):
#########################
# Preprocessing #
#########################
self.data = ["Thesis", "LiTS"]
self.root_dir = '/home/rgunti/data/{}'.format(self.data[0])
self.raw_data_dir = '{}/data_raw/data/'.format(self.root_dir)
self.raw_seg_dir = '{}/data_raw/seg/'.format(self.root_dir)
self.pp_dir = '{}/data_pp'.format(self.root_dir)
self.pp_dir_wocrop = '{}/data_pp_wocrop'.format(self.root_dir)
self.pp_dir_int = '{}/data_pp_int'.format(self.root_dir)
self.pp_dir_int_wocrop = '{}/data_pp_int_wocrop'.format(self.root_dir)
self.target_spacing = (1.0, 1.0, 2.5)
if server_env:
self.root_dir = "/content/drive/My\' \'Drive/Thesis/Thesis/"
self.raw_data_dir = '{}/Dataset/data/'.format(self.root_dir)
self.raw_seg_dir = '{}/Dataset/seg/'.format(self.root_dir)
self.pp_dir = '{}/data_pp'.format(self.root_dir)
#########################
# I/O #
#########################
# one out of [2, 3]. dimension the model operates in.
self.dim = 3
# one out of ['mrcnn', 'retina_net', 'retina_unet', 'detection_unet', 'ufrcnn', 'decoupled_refinement'].
self.model = 'retina_net'
DefaultConfigs.__init__(self, self.model, server_env, self.dim)
# int [0 < dataset_size]. select n patients from dataset for prototyping. If None, all data is used.
self.select_prototype_subset = None
self.subset_ixs = None
self.subset_pids = None
self.hold_out_test_set = True
self.data_dest = ''
# path to preprocessed data.
# self.pp_name = 'data_pp'
# self.pp_name = 'data_pp_int'
# self.pp_name = 'data_pp_wocrop'
self.pp_name = 'data_pp_int_wocrop'
self.input_df_name = 'info_df.pickle'
self.pp_data_path = '{}/{}/'.format(self.root_dir, self.pp_name)
# change if test_data in separate folder.
self.pp_test_data_path = self.pp_data_path
# settings for deployment in cloud.
if server_env:
# path to preprocessed data.
# self.pp_name = 'lidc_mdt_npz'
self.crop_name = 'pp_fg_slices_packed'
# self.pp_data_path = '/datasets/datasets_ramien/lidc_exp/data/{}'.format(self.pp_name)
self.data_dest = '/content/'
self.pp_test_data_path = self.pp_data_path
self.select_prototype_subset = None
#########################
# Data Loader #
#########################
# select modalities from preprocessed data
self.channels = [0]
self.n_channels = len(self.channels)
# patch_size to be used for training. pre_crop_size is the patch_size before data augmentation.
self.pre_crop_size_2D = [256, 256]
self.patch_size_2D = [224, 224]
self.use_big_patch = 0
if self.use_big_patch:
self.pre_crop_size_3D = [256, 256, 112]
self.patch_size_3D = [224, 224, 96]
else:
self.pre_crop_size_3D = [156, 156, 96]
self.patch_size_3D = [128, 128, 64]
self.pre_crop_size = self.pre_crop_size_2D if self.dim == 2 else self.pre_crop_size_3D
self.patch_size = self.patch_size_2D if self.dim == 2 else self.patch_size_3D
# ratio of free sampled batch elements before class balancing is triggered
# (>0 to include "empty"/background patches.)
self.batch_sample_slack = 0.2
# self.batch_sample_slack = 0.5 if self.dim == 2 else 1.0
# set 2D network to operate in 3D images.
self.merge_2D_to_3D_preds = False
# feed +/- n neighbouring slices into channel dimension. set to None for no context.
self.n_3D_context = None
if self.n_3D_context is not None and self.dim == 2:
self.n_channels *= (self.n_3D_context * 2 + 1)
#########################
# Architecture #
#########################
self.start_filts = 48 if self.dim == 2 else 32
self.end_filts = self.start_filts * 4 if self.dim == 2 else self.start_filts * 2
self.res_architecture = 'resnet50' # 'resnet101' , 'resnet50'
self.norm = 'batch_norm' # one of None, 'instance_norm', 'batch_norm'
self.weight_decay = 0
# one of 'xavier_uniform', 'xavier_normal', or 'kaiming_normal', None (=default = 'kaiming_uniform')
self.weight_init = None
# Path to checkpoint of an experiment. Models loads only the matching keys from net.state_dict
self.pre_train_path = None
#########################
# Schedule / Selection #
#########################
self.num_epochs = 1200
self.num_train_batches = 50 if self.dim == 2 else 50
self.batch_size = 64 if self.dim == 2 else 1 if self.use_big_patch else 4
self.do_validation = True if self.select_prototype_subset is None else False
# decide whether to validate on entire patient volumes (like testing) or sampled patches (like training)
# the former is morge accurate, while the latter is faster (depending on volume size)
self.val_mode = 'val_sampling' # one of 'val_sampling' , 'val_patient'
if self.val_mode == 'val_patient':
# if 'None' iterates over entire val_set once.
self.max_val_patients = None
if self.val_mode == 'val_sampling':
self.num_val_batches = 10
#########################
# Testing / Plotting #
#########################
# set the top-n-epochs to be saved for temporal averaging in testing.
self.save_n_models = 5
self.test_n_epochs = 1
# set a minimum epoch number for saving in case of instabilities in the first phase of training.
self.min_save_thresh = 0 if self.dim == 2 else 0
self.test_aug = False
# choose list from 'patient', 'rois'
self.report_score_level = ['rois']
# self.class_dict = {1: 'benign', 2: 'malignant'} # 0 is background.
self.class_dict = {1: 'lesion'} # 0 is background.
# self.patient_class_of_interest = 2 # patient metrics are only plotted for one class.
self.patient_class_of_interest = 1
# list of ious to be evaluated for ap-scoring.
self.ap_match_ious = [0.1]
# self.model_selection_criteria = ['malignant_ap', 'benign_ap'] # criteria to average over for saving epochs.
self.model_selection_criteria = ['lesion_ap']
# minimum confidence value to select predictions for evaluation.
self.min_det_thresh = 0
# analysis of the hyper-parameter cf.min_det_thresh, for optimization on validation set.
self.scan_det_thresh = False
# threshold for clustering predictions together (wcs = weighted cluster scoring).
# needs to be >= the expected overlap of predictions coming from one model (typically NMS threshold).
# if too high, preds of the same object are separate clusters.
self.wcs_iou = 1e-5
self.plot_prediction_histograms = True
self.plot_stat_curves = True
#########################
# Data Augmentation #
#########################
self.da_kwargs = {
'do_elastic_deform': True,
'alpha': (0., 1500.),
'sigma': (30., 50.),
'do_rotation': True,
'angle_x': (0., 0. * np.pi),
'angle_y': (0., 0),
'angle_z': (0., 0),
'do_scale': True,
'scale': (0.8, 1.2),
'random_crop': True,
'rand_crop_dist': (self.patch_size[0] / 2. - 3, self.patch_size[1] / 2. - 3),
'border_mode_data': 'constant',
'border_cval_data': 0,
'order_data': 1
}
if self.dim == 3:
self.da_kwargs['rand_crop_dist'] = (
self.patch_size[0] / 2. - 3, self.patch_size[1] / 2. - 3, self.patch_size[2] / 2. - 3)
self.da_kwargs['do_elastic_deform'] = True
self.da_kwargs['angle_x'] = (0, 0.0)
self.da_kwargs['angle_y'] = (0, 0.0) # must be 0!!
self.da_kwargs['angle_z'] = (0., 2 * np.pi)
#########################
# Add model specifics #
#########################
{'detection_unet': self.add_det_unet_configs,
'mrcnn': self.add_mrcnn_configs,
'ufrcnn': self.add_mrcnn_configs,
'retina_net': self.add_mrcnn_configs,
'retina_unet': self.add_mrcnn_configs,
'decoupled_refinement': self.add_mrcnn_configs,
}[self.model]()