def build_detection_semisup_train_loader_two_crops()

in ubteacher/data/build.py [0:0]

• 63 lines of code
• 12 McCabe index (conditional complexity)

def build_detection_semisup_train_loader_two_crops(cfg, mapper=None):
    if cfg.DATASETS.CROSS_DATASET:  # cross-dataset (e.g., coco-additional)
        label_dicts = get_detection_dataset_dicts(
            cfg.DATASETS.TRAIN_LABEL,
            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,
        )
        unlabel_dicts = get_detection_dataset_dicts(
            cfg.DATASETS.TRAIN_UNLABEL,
            filter_empty=False,
            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,
        )
    else:  # different degree of supervision (e.g., COCO-supervision)
        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,
        )

    label_dataset = DatasetFromList(label_dicts, copy=False)
    # exclude the labeled set from unlabeled dataset
    unlabel_dataset = DatasetFromList(unlabel_dicts, copy=False)
    # include the labeled set in unlabel dataset
    # unlabel_dataset = DatasetFromList(dataset_dicts, copy=False)

    if mapper is None:
        mapper = DatasetMapper(cfg, True)
    label_dataset = MapDataset(label_dataset, mapper)
    unlabel_dataset = MapDataset(unlabel_dataset, mapper)

    sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
    logger = logging.getLogger(__name__)
    logger.info("Using training sampler {}".format(sampler_name))
    if sampler_name == "TrainingSampler":
        label_sampler = TrainingSampler(len(label_dataset))
        unlabel_sampler = TrainingSampler(len(unlabel_dataset))
    elif sampler_name == "RepeatFactorTrainingSampler":
        raise NotImplementedError("{} not yet supported.".format(sampler_name))
    else:
        raise ValueError("Unknown training sampler: {}".format(sampler_name))
    return build_semisup_batch_data_loader_two_crop(
        (label_dataset, unlabel_dataset),
        (label_sampler, unlabel_sampler),
        cfg.SOLVER.IMG_PER_BATCH_LABEL,
        cfg.SOLVER.IMG_PER_BATCH_UNLABEL,
        aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
        num_workers=cfg.DATALOADER.NUM_WORKERS,
    )