def build_as_torch_loader(root, mode="train", batch_size=16, num_workers=0):
if mode == "train":
train_dataset = cgrcnn_dataset_torch(root, mode=mode)
train_sampler = torch.utils.data.RandomSampler(train_dataset,
replacement=False,
num_samples=None,
generator=None)
trainloader = build_batch_data_loader(dataset=train_dataset,
sampler=train_sampler,
total_batch_size=batch_size,
aspect_ratio_grouping=False,
num_workers=num_workers)
return trainloader
elif mode == "test":
test_dataset = cgrcnn_dataset_torch(root, mode=mode)
test_sampler = torch.utils.data.RandomSampler(test_dataset,
replacement=False,
num_samples=None,
generator=None)
testloader = build_batch_data_loader(dataset=test_dataset,
sampler=test_sampler,
total_batch_size=batch_size,
aspect_ratio_grouping=False,
num_workers=num_workers)
return testloader
def build_custom_train_loader(cfg, mapper=None):
"""
Modified from detectron2.data.build.build_custom_train_loader, but supports
different samplers
"""
source_aware = cfg.DATALOADER.SOURCE_AWARE
if source_aware:
dataset_dicts = get_detection_dataset_dicts_with_source(
cfg.DATASETS.TRAIN,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN
if cfg.MODEL.LOAD_PROPOSALS else None,
)
sizes = [0 for _ in range(len(cfg.DATASETS.TRAIN))]
for d in dataset_dicts:
sizes[d['dataset_source']] += 1
print('dataset sizes', sizes)
else:
dataset_dicts = get_detection_dataset_dicts(
cfg.DATASETS.TRAIN,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN
if cfg.MODEL.LOAD_PROPOSALS else None,
)
dataset = DatasetFromList(dataset_dicts, copy=False)
if mapper is None:
assert 0
# mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
logger = logging.getLogger(__name__)
logger.info("Using training sampler {}".format(sampler_name))
# TODO avoid if-else?
if sampler_name == "TrainingSampler":
sampler = TrainingSampler(len(dataset))
elif sampler_name == "MultiDatasetSampler":
assert source_aware
sampler = MultiDatasetSampler(cfg, sizes, dataset_dicts)
elif sampler_name == "RepeatFactorTrainingSampler":
repeat_factors = RepeatFactorTrainingSampler.repeat_factors_from_category_frequency(
dataset_dicts, cfg.DATALOADER.REPEAT_THRESHOLD)
sampler = RepeatFactorTrainingSampler(repeat_factors)
elif sampler_name == "ClassAwareSampler":
sampler = ClassAwareSampler(dataset_dicts)
else:
raise ValueError("Unknown training sampler: {}".format(sampler_name))
return build_batch_data_loader(
dataset,
sampler,
cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS,
)
def build_detection_train_loader(cfg: CfgNode, mapper=None):
"""
A data loader is created in a way similar to that of Detectron2.
The main differences are:
- it allows to combine datasets with different but compatible object category sets
The data loader is created by the following steps:
1. Use the dataset names in config to query :class:`DatasetCatalog`, and obtain a list of dicts.
2. Start workers to work on the dicts. Each worker will:
* Map each metadata dict into another format to be consumed by the model.
* Batch them by simply putting dicts into a list.
The batched ``list[mapped_dict]`` is what this dataloader will return.
Args:
cfg (CfgNode): the config
mapper (callable): a callable which takes a sample (dict) from dataset and
returns the format to be consumed by the model.
By default it will be `DatasetMapper(cfg, True)`.
Returns:
an infinite iterator of training data
"""
_add_category_whitelists_to_metadata(cfg)
_add_category_maps_to_metadata(cfg)
dataset_dicts = combine_detection_dataset_dicts(
cfg.DATASETS.TRAIN,
keep_instance_predicate=_get_train_keep_instance_predicate(cfg),
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN if cfg.MODEL.LOAD_PROPOSALS else None,
)
dataset = DatasetFromList(dataset_dicts, copy=False)
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
logger = logging.getLogger(__name__)
logger.info("Using training sampler {}".format(sampler_name))
if sampler_name == "TrainingSampler":
sampler = TrainingSampler(len(dataset))
elif sampler_name == "RepeatFactorTrainingSampler":
repeat_factors = RepeatFactorTrainingSampler.repeat_factors_from_category_frequency(
dataset_dicts, cfg.DATALOADER.REPEAT_THRESHOLD
)
sampler = RepeatFactorTrainingSampler(repeat_factors)
else:
raise ValueError("Unknown training sampler: {}".format(sampler_name))
return build_batch_data_loader(
dataset,
sampler,
cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS,
)
def build_detection_train_loader(cfg, mapper=None):
"""
A data loader is created by the following steps:
1. Use the dataset names in config to query :class:`DatasetCatalog`, and obtain a list of dicts.
2. Coordinate a random shuffle order shared among all processes (all GPUs)
3. Each process spawn another few workers to process the dicts. Each worker will:
* Map each metadata dict into another format to be consumed by the model.
* Batch them by simply putting dicts into a list.
The batched ``list[mapped_dict]`` is what this dataloader will yield.
Args:
cfg (CfgNode): the config
mapper (callable): a callable which takes a sample (dict) from dataset and
returns the format to be consumed by the model.
By default it will be `DatasetMapper(cfg, True)`.
Returns:
an infinite iterator of training data
"""
dataset_dicts = fsod_get_detection_dataset_dicts(
cfg.DATASETS.TRAIN,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN
if cfg.MODEL.LOAD_PROPOSALS else None,
)
dataset = DatasetFromList(dataset_dicts, copy=False)
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
logger = logging.getLogger(__name__)
logger.info("Using training sampler {}".format(sampler_name))
# TODO avoid if-else?
if sampler_name == "TrainingSampler":
sampler = TrainingSampler(len(dataset))
elif sampler_name == "RepeatFactorTrainingSampler":
repeat_factors = RepeatFactorTrainingSampler.repeat_factors_from_category_frequency(
dataset_dicts, cfg.DATALOADER.REPEAT_THRESHOLD)
sampler = RepeatFactorTrainingSampler(repeat_factors)
else:
raise ValueError("Unknown training sampler: {}".format(sampler_name))
return build_batch_data_loader(
dataset,
sampler,
cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS,
)
def build_detection_semisup_train_loader(cfg, mapper=None):
dataset_dicts = get_detection_dataset_dicts(
cfg.DATASETS.TRAIN,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN
if cfg.MODEL.LOAD_PROPOSALS else None,
)
# Divide into labeled and unlabeled sets according to supervision percentage
label_dicts, unlabel_dicts = divide_label_unlabel(
dataset_dicts,
cfg.DATALOADER.SUP_PERCENT,
cfg.DATALOADER.RANDOM_DATA_SEED,
cfg.DATALOADER.RANDOM_DATA_SEED_PATH,
)
dataset = DatasetFromList(label_dicts, copy=False)
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
logger = logging.getLogger(__name__)
logger.info("Using training sampler {}".format(sampler_name))
if sampler_name == "TrainingSampler":
sampler = TrainingSampler(len(dataset))
elif sampler_name == "RepeatFactorTrainingSampler":
repeat_factors = (
RepeatFactorTrainingSampler.repeat_factors_from_category_frequency(
label_dicts, cfg.DATALOADER.REPEAT_THRESHOLD))
sampler = RepeatFactorTrainingSampler(repeat_factors)
else:
raise ValueError("Unknown training sampler: {}".format(sampler_name))
# list num of labeled and unlabeled
logger.info("Number of training samples " + str(len(dataset)))
logger.info("Supervision percentage " + str(cfg.DATALOADER.SUP_PERCENT))
return build_batch_data_loader(
dataset,
sampler,
cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS,
)
def build_detection_train_loader(cfg):
"""Builds a data loader for the baseline trainer with support of training on the subset of labeled data only.
Most of code comes from `d2.data.build.build_detection_train_loader()`, see it for more details.
"""
# CSD: check config is supported
assert cfg.DATALOADER.SAMPLER_TRAIN == "TrainingSampler", "Unsupported training sampler: {}".format(
cfg.DATALOADER.SAMPLER_TRAIN)
# Original code
dataset = get_detection_dataset_dicts(
cfg.DATASETS.TRAIN,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN
if cfg.MODEL.LOAD_PROPOSALS else None,
)
# CSD: subsample the dataset if needed
dataset = check_subsample_dataset(dataset, cfg)
if comm.is_main_process(): # Log counts
logger = setup_logger(name=__name__)
logger.debug("Number of images in the dataset: {}".format(
len(dataset)))
_log_api_usage("dataset." + cfg.DATASETS.TRAIN[0])
# Original code
mapper = DatasetMapper(cfg, True)
sampler = TrainingSampler(len(dataset))
dataset = DatasetFromList(dataset, copy=False)
dataset = MapDataset(dataset, mapper)
sampler = TrainingSampler(len(dataset))
assert isinstance(sampler, torch.utils.data.sampler.Sampler)
return build_batch_data_loader(
dataset,
sampler,
cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS,
)
return len(self.sample_name)
if __name__ == "__main__":
batch_size = 4
np.random.seed(12138)
cwd = os.getcwd()
root = cwd + "/data/training_data/"
# root = "/media/fanuc/35B4BBB7636A09EB/Xinghao/ContrastiveGrasp/data/training_data/"
train_dataset = cgrcnn_dataset_torch(root, mode="train")
train_sampler = torch.utils.data.RandomSampler(train_dataset,
replacement=False,
num_samples=None,
generator=None)
trainloader = build_batch_data_loader(dataset=train_dataset,
sampler=train_sampler,
total_batch_size=batch_size,
aspect_ratio_grouping=False,
num_workers=8)
img = []
for i, inputs in enumerate(trainloader, 0):
img += [input_[0]["image"][0] for input_ in inputs]
if i == 250:
count = len(img)
img_sum = torch.stack(img, dim=0).sum(dim=0) / count
mean, std = torch.mean(img_sum), torch.std(img_sum)
print("OK")