def val_dataloader(self):
if self.data_config.dataset_name == "normal_dataset":
transform = self._3d_augmenation("valid")
else:
transform = None
if self.use_ddp:
sampler = torch.utils.data.distributed.DistributedSampler(
self.valid_dataset, shuffle=False)
valid_loader = DataLoader(
self.valid_dataset,
batch_size=self.test_config.batch_size,
num_workers=self.cpu_count,
pin_memory=True,
sampler=sampler,
gpu_transforms=transform,
)
else:
sampler = torch.utils.data.sampler.SequentialSampler(
self.valid_dataset)
valid_loader = DataLoader(
self.valid_dataset,
batch_size=self.test_config.batch_size,
pin_memory=True,
sampler=sampler,
num_workers=self.cpu_count,
gpu_transforms=transform,
)
return valid_loader
def train_dataloader(self):
if self.data_config.dataset_name == "normal_dataset":
transform = self._3d_augmenation("train")
else:
transform = None
if self.use_ddp:
sampler = torch.utils.data.distributed.DistributedSampler(
self.train_dataset, shuffle=True)
train_loader = DataLoader(
self.train_dataset,
batch_size=self.train_config.batch_size,
num_workers=self.cpu_count,
pin_memory=True,
sampler=sampler,
drop_last=True,
gpu_transforms=transform,
)
else:
sampler = torch.utils.data.sampler.RandomSampler(
self.train_dataset)
train_loader = DataLoader(
self.train_dataset,
batch_size=self.train_config.batch_size,
pin_memory=True,
sampler=sampler,
drop_last=True,
num_workers=self.cpu_count,
gpu_transforms=transform,
)
return train_loader
def train_dataloader(self):
transforms_augment_cpu = []
transforms_augment = []
#transforms_augment_cpu.append(rtr.intensity.RandomAddValue(UniformParameter(-0.2, 0.2)))
#cpu_transforms = Compose(transforms_augment_cpu)
keys = ('data', 'label')
# transforms_augment.append(rtr.GaussianNoise(0., 0.05))
transforms_augment.append(rtr.Rot90(dims=(0, 1, 2), keys=keys))
transforms_augment.append(rtr.Mirror(dims=(0, 1, 2), keys=keys))
#transforms_augment.append(ElasticDeformer3d(32, 4, keys=keys,
# interp_mode={ 'data': 'linear', 'label': 'nearest' }))
#transforms_augment.append(rtr.BaseAffine(
# scale=UniformParameter(0.95, 1.05),
# rotation=UniformParameter(-45, 45), degree=True,
# translation=UniformParameter(-0.05, 0.05),
# keys=('data', 'label'),
# interpolation_mode='nearest'))
gpu_transforms = Compose(transforms_augment)
return DataLoader(self.train_dataset,
batch_size=self.hparams.batch_size,
num_workers=self.hparams.num_loader_workers,
shuffle=True,
#batch_transforms=cpu_transforms,
gpu_transforms=gpu_transforms,
pin_memory=True)
def test_progressive_resize_integration(self):
sizes = [1, 3, 6]
scheduler = SizeStepScheduler([1, 2], [1, 3, 6])
trafo = ProgressiveResize(scheduler)
dset = [self.batch_dict] * 10
loader = DataLoader(dset, num_workers=4, batch_transforms=trafo)
data_shape = [tuple(i["data"].shape) for i in loader]
self.assertIn((1, 1, 1, 1, 1), data_shape)
# self.assertIn((1, 1, 3, 3, 3), data_shape)
self.assertIn((1, 1, 6, 6, 6), data_shape)
def val_dataloader(self):
gpu_transforms = []
keys = ('data', 'label')
gpu_transforms.append(rtr.Rot90(dims=(0, 1, 2), keys=keys))
gpu_transforms.append(rtr.Mirror(dims=(0, 1, 2), keys=keys))
gpu_transforms = Compose(gpu_transforms)
return DataLoader(self.val_dataset,
batch_size=2 * self.hparams.batch_size,
num_workers=self.hparams.num_loader_workers,
shuffle=False,
gpu_transforms=gpu_transforms,
pin_memory=True)
def train_dataloader(self):
keys = ('data', 'label')
transforms_augment = []
transforms_augment.append(rtr.Rot90(dims=(0, 1, 2), keys=keys))
transforms_augment.append(rtr.Mirror(dims=(0, 1, 2), keys=keys))
#transforms_augment.append(ElasticDeformer3d(32, 4, keys=keys,
# interp_mode={ 'data': 'linear', 'label': 'nearest' }))
gpu_transforms = Compose(transforms_augment)
return DataLoader(self.train_dataset,
batch_size=self.hparams.batch_size,
num_workers=self.hparams.num_loader_workers,
shuffle=True,
gpu_transforms=gpu_transforms,
pin_memory=True)
def test_dataloader(self):
if self.data_config.dataset_name == "normal_dataset":
transform = self._3d_augmenation("test")
else:
transform = None
sampler = torch.utils.data.sampler.SequentialSampler(self.test_dataset)
test_loader = DataLoader(
self.test_dataset,
batch_size=self.test_config.batch_size,
pin_memory=True,
sampler=sampler,
num_workers=self.cpu_count,
gpu_transforms=transform,
)
return test_loader
def val_dataloader(self):
gpu_transforms = []
gpu_transforms.append(rtr.Rot90(dims=(0, 1, 2), keys=('data', 'label')))
gpu_transforms.append(rtr.Mirror(dims=(0, 1, 2), keys=('data', 'label')))
gpu_transforms = Compose(gpu_transforms)
# batch_transforms = []
# batch_transforms.append(BatchRandomCrop(self.hparams.crop_size, bs=1, dist=0, keys=('data', 'label')))
# batch_transforms = Compose(batch_transforms)
return DataLoader(self.val_dataset,
batch_size=2 * self.hparams.batch_size,
num_workers=self.hparams.num_loader_workers,
shuffle=False,
# batch_transforms=batch_transforms,
gpu_transforms=gpu_transforms,
pin_memory=True)