def get_train_dataset(cfg, root_dataset_path, train_dataset_name,
eval_binary_path):
# We only create the train dataset if we need PCA or whitening training.
# Otherwise not.
if cfg.IMG_RETRIEVAL.SHOULD_TRAIN_PCA_OR_WHITENING:
train_data_path = f"{root_dataset_path}/{train_dataset_name}"
assert PathManager.exists(
train_data_path), f"Unknown path: {train_data_path}"
num_samples = 10 if cfg.IMG_RETRIEVAL.DEBUG_MODE else None
if is_revisited_dataset(train_dataset_name):
train_dataset = RevisitedInstanceRetrievalDataset(
train_dataset_name, root_dataset_path)
elif is_whiten_dataset(train_dataset_name):
train_dataset = WhiteningTrainingImageDataset(
train_data_path,
cfg.IMG_RETRIEVAL.WHITEN_IMG_LIST,
num_samples=num_samples,
)
else:
train_dataset = InstanceRetrievalDataset(train_data_path,
eval_binary_path,
num_samples=num_samples)
else:
train_dataset = None
return train_dataset
def get_eval_dataset(cfg, root_dataset_path, eval_dataset_name, eval_binary_path):
eval_data_path = f"{root_dataset_path}/{eval_dataset_name}"
assert PathManager.exists(eval_data_path), f"Unknown path: {eval_data_path}"
num_samples = (
None
if cfg.IMG_RETRIEVAL.NUM_DATABASE_SAMPLES == -1
else cfg.IMG_RETRIEVAL.NUM_DATABASE_SAMPLES
)
if is_revisited_dataset(eval_dataset_name):
eval_dataset = RevisitedInstanceRetrievalDataset(
eval_dataset_name, root_dataset_path, num_samples=num_samples
)
elif is_instre_dataset(eval_dataset_name):
eval_dataset = InstreDataset(eval_data_path, num_samples=num_samples)
elif is_copdays_dataset(eval_dataset_name):
eval_dataset = CopyDaysDataset(
data_path=eval_data_path,
num_samples=num_samples,
use_distractors=cfg.IMG_RETRIEVAL.USE_DISTRACTORS,
)
else:
eval_dataset = InstanceRetrievalDataset(
eval_data_path, eval_binary_path, num_samples=num_samples
)
return eval_dataset
def get_eval_dataset(cfg, root_dataset_path, eval_dataset_name, eval_binary_path):
eval_data_path = f"{root_dataset_path}/{eval_dataset_name}"
assert PathManager.exists(eval_data_path), f"Unknown path: {eval_data_path}"
num_samples = 20 if cfg.IMG_RETRIEVAL.DEBUG_MODE else None
if is_revisited_dataset(eval_dataset_name):
eval_dataset = RevisitedInstanceRetrievalDataset(
eval_dataset_name, root_dataset_path
)
elif is_instre_dataset(eval_dataset_name):
eval_dataset = InstreDataset(eval_data_path, num_samples=num_samples)
else:
eval_dataset = InstanceRetrievalDataset(
eval_data_path, eval_binary_path, num_samples=num_samples
)
return eval_dataset
def get_train_dataset(cfg, root_dataset_path, train_dataset_name, eval_binary_path):
# We only create the train dataset if we need PCA or whitening training.
# Otherwise not.
if cfg.IMG_RETRIEVAL.TRAIN_PCA_WHITENING:
train_data_path = f"{root_dataset_path}/{train_dataset_name}"
assert PathManager.exists(train_data_path), f"Unknown path: {train_data_path}"
num_samples = (
None
if cfg.IMG_RETRIEVAL.NUM_TRAINING_SAMPLES == -1
else cfg.IMG_RETRIEVAL.NUM_TRAINING_SAMPLES
)
if is_revisited_dataset(train_dataset_name):
train_dataset = RevisitedInstanceRetrievalDataset(
train_dataset_name, root_dataset_path, num_samples=num_samples
)
elif is_whiten_dataset(train_dataset_name):
train_dataset = WhiteningTrainingImageDataset(
train_data_path,
cfg.IMG_RETRIEVAL.WHITEN_IMG_LIST,
num_samples=num_samples,
)
elif is_copdays_dataset(train_dataset_name):
train_dataset = CopyDaysDataset(
data_path=train_data_path,
num_samples=num_samples,
use_distractors=cfg.IMG_RETRIEVAL.USE_DISTRACTORS,
)
elif is_oxford_paris_dataset(train_dataset_name):
train_dataset = InstanceRetrievalDataset(
train_data_path, eval_binary_path, num_samples=num_samples
)
else:
train_dataset = GenericInstanceRetrievalDataset(
train_data_path, num_samples=num_samples
)
else:
train_dataset = None
return train_dataset