def __init__(self, args):
self.args = args
self.mode = self.args.exec_mode
task_code = get_task_code(self.args)
self.data = os.path.join(self.args.data, task_code)
self.results = os.path.join(self.args.results, task_code)
if self.mode == "test":
self.data = os.path.join(self.data, "test")
self.results = os.path.join(self.results, "test")
self.vpf = self.args.vpf
self.imgs = self.load_files("*x.npy")
self.lbls = self.load_files("*y.npy")
def __init__(self, args):
self.args = args
self.ct_min = 0
self.ct_max = 0
self.ct_mean = 0
self.ct_std = 0
self.target_spacing = None
self.task = args.task
self.task_code = get_task_code(args)
self.patch_size = patch_size[self.task_code]
self.training = args.exec_mode == "training"
self.data_path = os.path.join(args.data, task[args.task])
self.results = os.path.join(args.results, self.task_code)
if not self.training:
self.results = os.path.join(self.results, "test")
self.metadata = json.load(open(os.path.join(self.data_path, "dataset.json"), "r"))
self.modality = self.metadata["modality"]["0"]
self.crop_foreg = transforms.CropForegroundd(keys=["image", "label"], source_key="image")
self.normalize_intensity = transforms.NormalizeIntensity(nonzero=True, channel_wise=True)
def __init__(self, args):
super().__init__()
self.args = args
self.tfrecords_train = []
self.tfrecords_val = []
self.tfrecords_test = []
self.train_idx = []
self.val_idx = []
self.test_idx = []
self.kfold = KFold(n_splits=self.args.nfolds, shuffle=True, random_state=12345)
self.data_path = os.path.join(self.args.data, get_task_code(self.args))
if self.args.exec_mode == "predict" and not args.benchmark:
self.data_path = os.path.join(self.data_path, "test")
configs = get_config_file(self.args)
self.kwargs = {
"dim": self.args.dim,
"patch_size": configs["patch_size"],
"seed": self.args.seed,
"gpus": self.args.gpus,
"num_workers": self.args.num_workers,
"oversampling": self.args.oversampling,
"create_idx": self.args.create_idx,
"benchmark": self.args.benchmark,
}
def __init__(self, args):
self.args = args
self.target_spacing = None
self.task = args.task
self.task_code = get_task_code(args)
self.verbose = args.verbose
self.patch_size = patch_size[self.task_code]
self.training = args.exec_mode == "training"
self.data_path = os.path.join(args.data, task[args.task])
metadata_path = os.path.join(self.data_path, "dataset.json")
self.metadata = json.load(open(metadata_path, "r"))
self.modality = self.metadata["modality"]["0"]
self.results = os.path.join(args.results, self.task_code)
self.ct_min, self.ct_max, self.ct_mean, self.ct_std = (0,) * 4
if not self.training:
self.results = os.path.join(self.results, self.args.exec_mode)
self.crop_foreg = transforms.CropForegroundd(keys=["image", "label"], source_key="image")
nonzero = True if self.modality != "CT" else False # normalize only non-zero region for MRI
self.normalize_intensity = transforms.NormalizeIntensity(nonzero=nonzero, channel_wise=True)
if self.args.exec_mode == "val":
dataset_json = json.load(open(metadata_path, "r"))
dataset_json["val"] = dataset_json["training"]
with open(metadata_path, "w") as outfile:
json.dump(dataset_json, outfile)
default="training",
choices=["training", "test"],
help="Mode for data preprocessing",
)
parser.add_argument("--task",
type=str,
help="Number of task to be run. MSD uses numbers 01-10")
parser.add_argument("--dim",
type=int,
default=3,
choices=[2, 3],
help="Data dimension to prepare")
parser.add_argument("--n_jobs",
type=int,
default=-1,
help="Number of parallel jobs for data preprocessing")
parser.add_argument("--vpf", type=int, default=1, help="Volumes per tfrecord")
if __name__ == "__main__":
args = parser.parse_args()
start = time.time()
Preprocessor(args).run()
Converter(args).run()
task_code = get_task_code(args)
path = os.path.join(args.data, task_code)
if args.exec_mode == "test":
path = os.path.join(path, "test")
call(f'find {path} -name "*.npy" -print0 | xargs -0 rm', shell=True)
end = time.time()
print(f"Preprocessing time: {(end - start):.2f}")