def convert_h5(data_dir,
label_dir,
data_split,
train_volumes,
test_volumes,
f,
data_id,
remap_config='Neo',
orientation=preprocessor.ORIENTATION['coronal']):
# Data splitting
if data_split:
train_file_paths, test_file_paths = apply_split(
data_split, data_dir, label_dir)
elif train_volumes and test_volumes:
train_file_paths = du.load_file_paths(data_dir, label_dir, data_id,
train_volumes)
test_file_paths = du.load_file_paths(data_dir, label_dir, data_id,
test_volumes)
else:
raise ValueError(
'You must either provide the split ratio or a train, train dataset list'
)
reduce_slices = False #True #BORIS
print("Train dataset size: %d, Test dataset size: %d" %
(len(train_file_paths), len(test_file_paths)))
# loading,pre-processing and writing train data
print("===Train data===")
data_train, label_train, class_weights_train, weights_train, _ = du.load_dataset(
train_file_paths,
orientation,
remap_config=remap_config,
return_weights=True,
reduce_slices=reduce_slices, #BORIS
remove_black=True)
_write_h5(data_train,
label_train,
class_weights_train,
weights_train,
f,
mode='train')
# loading,pre-processing and writing test data
print("===Test data===")
data_test, label_test, class_weights_test, weights_test, _ = du.load_dataset(
test_file_paths,
orientation,
remap_config=remap_config,
return_weights=True,
reduce_slices=reduce_slices, #BORIS
remove_black=True)
_write_h5(data_test,
label_test,
class_weights_test,
weights_test,
f,
mode='test')
def apply_split(data_split, data_dir, label_dir):
file_paths = du.load_file_paths(data_dir, label_dir)
print("Total no of volumes to process : %d" % len(file_paths))
train_ratio, test_ratio = data_split.split(",")
train_len = int((int(train_ratio) / 100) * len(file_paths))
train_idx = np.random.choice(len(file_paths), train_len, replace=False)
test_idx = np.array(
[i for i in range(len(file_paths)) if i not in train_idx])
train_file_paths = [file_paths[i] for i in train_idx]
test_file_paths = [file_paths[i] for i in test_idx]
return train_file_paths, test_file_paths