def initialize(self, training=True, force_load_plans=False):
"""
removed deep supervision
:return:
"""
if not self.was_initialized:
maybe_mkdir_p(self.output_folder)
if force_load_plans or (self.plans is None):
self.load_plans_file()
self.process_plans(self.plans)
self.setup_DA_params()
self.folder_with_preprocessed_data = join(
self.dataset_directory,
self.plans['data_identifier'] + "_stage%d" % self.stage)
if training:
self.dl_tr, self.dl_val = self.get_basic_generators()
if self.unpack_data:
print("unpacking dataset")
unpack_dataset(self.folder_with_preprocessed_data)
print("done")
else:
print(
"INFO: Not unpacking data! Training may be slow due to that. Pray you are not using 2d or you "
"will wait all winter for your model to finish!")
assert self.deep_supervision_scales is None
self.tr_gen, self.val_gen = get_moreDA_augmentation(
self.dl_tr,
self.dl_val,
self.data_aug_params['patch_size_for_spatialtransform'],
self.data_aug_params,
deep_supervision_scales=self.deep_supervision_scales,
classes=None,
pin_memory=self.pin_memory)
self.print_to_log_file("TRAINING KEYS:\n %s" %
(str(self.dataset_tr.keys())),
also_print_to_console=False)
self.print_to_log_file("VALIDATION KEYS:\n %s" %
(str(self.dataset_val.keys())),
also_print_to_console=False)
else:
pass
self.initialize_network()
self.initialize_optimizer_and_scheduler()
assert isinstance(self.network,
(SegmentationNetwork, nn.DataParallel))
else:
self.print_to_log_file(
'self.was_initialized is True, not running self.initialize again'
)
self.was_initialized = True
def initialize(self, training=True, force_load_plans=False):
"""
For prediction of test cases just set training=False, this will prevent loading of training data and
training batchgenerator initialization
:param training:
:return:
"""
if not self.was_initialized:
if force_load_plans or (self.plans is None):
self.load_plans_file()
self.process_plans(self.plans)
self.setup_DA_params()
################# Here we wrap the loss for deep supervision ############
# we need to know the number of outputs of the network
net_numpool = len(self.net_num_pool_op_kernel_sizes)
# we give each output a weight which decreases exponentially (division by 2) as the resolution decreases
# this gives higher resolution outputs more weight in the loss
weights = np.array([1 / (2**i) for i in range(net_numpool)])
# we don't use the lowest 2 outputs. Normalize weights so that they sum to 1
mask = np.array([
True if i < net_numpool - 1 else False
for i in range(net_numpool)
])
weights[~mask] = 0
weights = weights / weights.sum()
self.ds_loss_weights = weights
# now wrap the loss
self.loss = MultipleOutputLoss2(self.loss, self.ds_loss_weights)
################# END ###################
self.folder_with_preprocessed_data = join(
self.dataset_directory,
self.plans['data_identifier'] + "_stage%d" % self.stage)
if training:
if not isdir(self.folder_with_segs_from_prev_stage):
raise RuntimeError(
"Cannot run final stage of cascade. Run corresponding 3d_lowres first and predict the "
"segmentations for the next stage")
self.dl_tr, self.dl_val = self.get_basic_generators()
if self.unpack_data:
print("unpacking dataset")
unpack_dataset(self.folder_with_preprocessed_data)
print("done")
else:
print(
"INFO: Not unpacking data! Training may be slow due to that. Pray you are not using 2d or you "
"will wait all winter for your model to finish!")
self.tr_gen, self.val_gen = get_moreDA_augmentation(
self.dl_tr,
self.dl_val,
self.data_aug_params['patch_size_for_spatialtransform'],
self.data_aug_params,
deep_supervision_scales=self.deep_supervision_scales,
pin_memory=self.pin_memory)
self.print_to_log_file("TRAINING KEYS:\n %s" %
(str(self.dataset_tr.keys())),
also_print_to_console=False)
self.print_to_log_file("VALIDATION KEYS:\n %s" %
(str(self.dataset_val.keys())),
also_print_to_console=False)
else:
pass
self.initialize_network()
self.initialize_optimizer_and_scheduler()
assert isinstance(self.network,
(SegmentationNetwork, nn.DataParallel))
else:
self.print_to_log_file(
'self.was_initialized is True, not running self.initialize again'
)
self.was_initialized = True
def initialize(self, training=True, force_load_plans=False):
"""
For prediction of test cases just set training=False, this will prevent loading of training data and
training batchgenerator initialization
:param training:
:return:
"""
if not self.was_initialized:
maybe_mkdir_p(self.output_folder)
if force_load_plans or (self.plans is None):
self.load_plans_file()
self.process_plans(self.plans)
self.setup_DA_params()
self.folder_with_preprocessed_data = join(
self.dataset_directory,
self.plans['data_identifier'] + "_stage%d" % self.stage)
if training:
self.dl_tr, self.dl_val = self.get_basic_generators()
if self.unpack_data:
if self.local_rank == 0:
print("unpacking dataset")
unpack_dataset(self.folder_with_preprocessed_data)
print("done")
else:
# we need to wait until worker 0 has finished unpacking
npz_files = subfiles(
self.folder_with_preprocessed_data,
suffix=".npz",
join=False)
case_ids = [i[:-4] for i in npz_files]
all_present = all([
isfile(
join(self.folder_with_preprocessed_data,
i + ".npy")) for i in case_ids
])
while not all_present:
print("worker", self.local_rank,
"is waiting for unpacking")
sleep(3)
all_present = all([
isfile(
join(self.folder_with_preprocessed_data,
i + ".npy")) for i in case_ids
])
# there is some slight chance that there may arise some error because dataloader are loading a file
# that is still being written by worker 0. We ignore this for now an address it only if it becomes
# relevant
# (this can occur because while worker 0 writes the file is technically present so the other workers
# will proceed and eventually try to read it)
else:
print(
"INFO: Not unpacking data! Training may be slow due to that. Pray you are not using 2d or you "
"will wait all winter for your model to finish!")
# setting weights for deep supervision losses
net_numpool = len(self.net_num_pool_op_kernel_sizes)
# we give each output a weight which decreases exponentially (division by 2) as the resolution decreases
# this gives higher resolution outputs more weight in the loss
weights = np.array([1 / (2**i) for i in range(net_numpool)])
# we don't use the lowest 2 outputs. Normalize weights so that they sum to 1
mask = np.array([
True if i < net_numpool - 1 else False
for i in range(net_numpool)
])
weights[~mask] = 0
weights = weights / weights.sum()
self.ds_loss_weights = weights
seeds_train = np.random.random_integers(
0, 99999, self.data_aug_params.get('num_threads'))
seeds_val = np.random.random_integers(
0, 99999,
max(self.data_aug_params.get('num_threads') // 2, 1))
print("seeds train", seeds_train)
print("seeds_val", seeds_val)
self.tr_gen, self.val_gen = get_moreDA_augmentation(
self.dl_tr,
self.dl_val,
self.data_aug_params['patch_size_for_spatialtransform'],
self.data_aug_params,
deep_supervision_scales=self.deep_supervision_scales,
seeds_train=seeds_train,
seeds_val=seeds_val)
self.print_to_log_file("TRAINING KEYS:\n %s" %
(str(self.dataset_tr.keys())),
also_print_to_console=False)
self.print_to_log_file("VALIDATION KEYS:\n %s" %
(str(self.dataset_val.keys())),
also_print_to_console=False)
else:
pass
self.initialize_network()
self.initialize_optimizer_and_scheduler()
self._maybe_init_amp()
self.network = DDP(self.network)
else:
self.print_to_log_file(
'self.was_initialized is True, not running self.initialize again'
)
self.was_initialized = True
def initialize(self, training=True, force_load_plans=False):
"""
- replaced get_default_augmentation with get_moreDA_augmentation
- only run this code once
- loss function wrapper for deep supervision
:param training:
:param force_load_plans:
:return:
"""
if not self.was_initialized:
maybe_mkdir_p(self.output_folder)
if force_load_plans or (self.plans is None):
self.load_plans_file()
self.process_plans(self.plans)
self.setup_DA_params()
################# Here configure the loss for deep supervision ############
net_numpool = len(self.net_num_pool_op_kernel_sizes)
weights = np.array([1 / (2 ** i) for i in range(net_numpool)])
mask = np.array([True if i < net_numpool - 1 else False for i in range(net_numpool)])
weights[~mask] = 0
weights = weights / weights.sum()
self.loss_weights = weights
################# END ###################
self.folder_with_preprocessed_data = join(self.dataset_directory, self.plans['data_identifier'] +
"_stage%d" % self.stage)
if training:
self.dl_tr, self.dl_val = self.get_basic_generators()
if self.unpack_data:
print("unpacking dataset")
unpack_dataset(self.folder_with_preprocessed_data)
print("done")
else:
print(
"INFO: Not unpacking data! Training may be slow due to that. Pray you are not using 2d or you "
"will wait all winter for your model to finish!")
self.tr_gen, self.val_gen = get_moreDA_augmentation(self.dl_tr, self.dl_val,
self.data_aug_params[
'patch_size_for_spatialtransform'],
self.data_aug_params,
deep_supervision_scales=self.deep_supervision_scales,
pin_memory=self.pin_memory)
self.print_to_log_file("TRAINING KEYS:\n %s" % (str(self.dataset_tr.keys())),
also_print_to_console=False)
self.print_to_log_file("VALIDATION KEYS:\n %s" % (str(self.dataset_val.keys())),
also_print_to_console=False)
else:
pass
self.initialize_network()
self.initialize_optimizer_and_scheduler()
assert isinstance(self.network, (SegmentationNetwork, nn.DataParallel))
else:
self.print_to_log_file('self.was_initialized is True, not running self.initialize again')
self.was_initialized = True
def initialize(self, training=True, force_load_plans=False):
"""
:param training:
:return:
"""
if not self.was_initialized:
maybe_mkdir_p(self.output_folder)
if force_load_plans or (self.plans is None):
self.load_plans_file()
self.process_plans(self.plans)
self.setup_DA_params()
self.folder_with_preprocessed_data = join(self.dataset_directory, self.plans['data_identifier'] +
"_stage%d" % self.stage)
if training:
self.dl_tr, self.dl_val = self.get_basic_generators()
if self.unpack_data:
if self.local_rank == 0:
print("unpacking dataset")
unpack_dataset(self.folder_with_preprocessed_data)
print("done")
distributed.barrier()
else:
print(
"INFO: Not unpacking data! Training may be slow due to that. Pray you are not using 2d or you "
"will wait all winter for your model to finish!")
# setting weights for deep supervision losses
net_numpool = len(self.net_num_pool_op_kernel_sizes)
# we give each output a weight which decreases exponentially (division by 2) as the resolution decreases
# this gives higher resolution outputs more weight in the loss
weights = np.array([1 / (2 ** i) for i in range(net_numpool)])
# we don't use the lowest 2 outputs. Normalize weights so that they sum to 1
mask = np.array([True if i < net_numpool - 1 else False for i in range(net_numpool)])
weights[~mask] = 0
weights = weights / weights.sum()
self.ds_loss_weights = weights
seeds_train = np.random.random_integers(0, 99999, self.data_aug_params.get('num_threads'))
seeds_val = np.random.random_integers(0, 99999, max(self.data_aug_params.get('num_threads') // 2, 1))
print("seeds train", seeds_train)
print("seeds_val", seeds_val)
self.tr_gen, self.val_gen = get_moreDA_augmentation(self.dl_tr, self.dl_val,
self.data_aug_params[
'patch_size_for_spatialtransform'],
self.data_aug_params,
deep_supervision_scales=self.deep_supervision_scales,
seeds_train=seeds_train,
seeds_val=seeds_val,
pin_memory=self.pin_memory)
self.print_to_log_file("TRAINING KEYS:\n %s" % (str(self.dataset_tr.keys())),
also_print_to_console=False)
self.print_to_log_file("VALIDATION KEYS:\n %s" % (str(self.dataset_val.keys())),
also_print_to_console=False)
else:
pass
self.initialize_network()
self.initialize_optimizer_and_scheduler()
self.network = DDP(self.network, device_ids=[self.local_rank])
else:
self.print_to_log_file('self.was_initialized is True, not running self.initialize again')
self.was_initialized = True
def initialize(self, training=True, force_load_plans=False):
"""
- replaced get_default_augmentation with get_moreDA_augmentation
- enforce to only run this code once
- loss function wrapper for deep supervision
:param training:
:param force_load_plans:
:return:
"""
if not self.was_initialized:
maybe_mkdir_p(self.output_folder)
if force_load_plans or (self.plans is None):
self.load_plans_file()
print("Patch size is %s" %
self.plans['plans_per_stage'][1]['patch_size'])
if self.norm_cfg == 'BN':
self.plans['plans_per_stage'][1]['batch_size'] = 8
# self.plans['plans_per_stage'][1]['batch_size'] = 1 #Debug
print("Batch size is %s" %
self.plans['plans_per_stage'][1]['batch_size'])
self.process_plans(self.plans)
self.setup_DA_params()
################# Here we wrap the loss for deep supervision ############
# we need to know the number of outputs of the network
net_numpool = len(self.net_num_pool_op_kernel_sizes)
# we give each output a weight which decreases exponentially (division by 2) as the resolution decreases
# this gives higher resolution outputs more weight in the loss
weights = np.array([1 / (2**i) for i in range(net_numpool)])
# we don't use the lowest 2 outputs. Normalize weights so that they sum to 1
mask = np.array([True] + [
True if i < net_numpool - 1 else False
for i in range(1, net_numpool)
])
weights[~mask] = 0
weights = weights / weights.sum()
self.ds_loss_weights = weights
# now wrap the loss
self.loss = MultipleOutputLoss2(self.loss, self.ds_loss_weights)
################# END ###################
self.folder_with_preprocessed_data = join(
self.dataset_directory,
self.plans['data_identifier'] + "_stage%d" % self.stage)
if training:
self.dl_tr, self.dl_val = self.get_basic_generators()
if self.unpack_data:
print("unpacking dataset")
unpack_dataset(self.folder_with_preprocessed_data)
print("done")
else:
print(
"INFO: Not unpacking data! Training may be slow due to that. Pray you are not using 2d or you "
"will wait all winter for your model to finish!")
self.tr_gen, self.val_gen = get_moreDA_augmentation(
self.dl_tr,
self.dl_val,
self.data_aug_params['patch_size_for_spatialtransform'],
self.data_aug_params,
deep_supervision_scales=self.deep_supervision_scales,
pin_memory=self.pin_memory)
self.print_to_log_file("TRAINING KEYS:\n %s" %
(str(self.dataset_tr.keys())),
also_print_to_console=False)
self.print_to_log_file("VALIDATION KEYS:\n %s" %
(str(self.dataset_val.keys())),
also_print_to_console=False)
else:
pass
self.initialize_network()
self.initialize_optimizer_and_scheduler()
assert isinstance(self.network,
(SegmentationNetwork, nn.DataParallel))
else:
self.print_to_log_file(
'self.was_initialized is True, not running self.initialize again'
)
self.was_initialized = True
