def from_config()

in mask_former/data/dataset_mappers/mask_former_semantic_dataset_mapper.py [0:0]

• 31 lines of code
• 3 McCabe index (conditional complexity)

    def from_config(cls, cfg, is_train=True):
        # Build augmentation
        augs = [
            T.ResizeShortestEdge(
                cfg.INPUT.MIN_SIZE_TRAIN,
                cfg.INPUT.MAX_SIZE_TRAIN,
                cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING,
            )
        ]
        if cfg.INPUT.CROP.ENABLED:
            augs.append(
                T.RandomCrop_CategoryAreaConstraint(
                    cfg.INPUT.CROP.TYPE,
                    cfg.INPUT.CROP.SIZE,
                    cfg.INPUT.CROP.SINGLE_CATEGORY_MAX_AREA,
                    cfg.MODEL.SEM_SEG_HEAD.IGNORE_VALUE,
                )
            )
        if cfg.INPUT.COLOR_AUG_SSD:
            augs.append(ColorAugSSDTransform(img_format=cfg.INPUT.FORMAT))
        augs.append(T.RandomFlip())

        # Assume always applies to the training set.
        dataset_names = cfg.DATASETS.TRAIN
        meta = MetadataCatalog.get(dataset_names[0])
        ignore_label = meta.ignore_label

        ret = {
            "is_train": is_train,
            "augmentations": augs,
            "image_format": cfg.INPUT.FORMAT,
            "ignore_label": ignore_label,
            "size_divisibility": cfg.INPUT.SIZE_DIVISIBILITY,
        }
        return ret