def __init__(self) -> None:
self._hooks: List[HookBase] = []
self.iter: int
self.start_iter: int
self.max_iter: int
self.storage: EventStorage
_log_api_usage("trainer." + self.__class__.__name__)
def build_model(cfg):
"""
Build the whole model architecture, defined by ``cfg.MODEL.META_ARCHITECTURE``.
Note that it does not load any weights from ``cfg``.
"""
meta_arch = cfg.MODEL.META_ARCHITECTURE
model = META_ARCH_REGISTRY.get(meta_arch)(cfg)
model.to(torch.device(cfg.MODEL.DEVICE))
_log_api_usage("modeling.meta_arch." + meta_arch)
return model
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,
)
def _train_loader_from_config(cfg, mapper=None, *, dataset=None, sampler=None):
if dataset is None:
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,
)
_log_api_usage("dataset." + cfg.DATASETS.TRAIN[0])
if mapper is None:
mapper = DatasetMapper(cfg, True)
if sampler is None:
sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
logger = logging.getLogger(__name__)
if isinstance(dataset, torchdata.IterableDataset):
logger.info("Not using any sampler since the dataset is IterableDataset.")
sampler = None
else:
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, cfg.DATALOADER.REPEAT_THRESHOLD
)
sampler = RepeatFactorTrainingSampler(repeat_factors)
elif sampler_name == "RandomSubsetTrainingSampler":
sampler = RandomSubsetTrainingSampler(
len(dataset), cfg.DATALOADER.RANDOM_SUBSET_RATIO
)
else:
raise ValueError("Unknown training sampler: {}".format(sampler_name))
return {
"dataset": dataset,
"sampler": sampler,
"mapper": mapper,
"total_batch_size": cfg.SOLVER.IMS_PER_BATCH,
"aspect_ratio_grouping": cfg.DATALOADER.ASPECT_RATIO_GROUPING,
"num_workers": cfg.DATALOADER.NUM_WORKERS,
}