def from_config()

in mask2former/maskformer_model.py [0:0]
53 lines of code
6 McCabe index (conditional complexity)

    def from_config(cls, cfg):
        backbone = build_backbone(cfg)
        sem_seg_head = build_sem_seg_head(cfg, backbone.output_shape())

        # Loss parameters:
        deep_supervision = cfg.MODEL.MASK_FORMER.DEEP_SUPERVISION
        no_object_weight = cfg.MODEL.MASK_FORMER.NO_OBJECT_WEIGHT

        # loss weights
        class_weight = cfg.MODEL.MASK_FORMER.CLASS_WEIGHT
        dice_weight = cfg.MODEL.MASK_FORMER.DICE_WEIGHT
        mask_weight = cfg.MODEL.MASK_FORMER.MASK_WEIGHT

        # building criterion
        matcher = HungarianMatcher(
            cost_class=class_weight,
            cost_mask=mask_weight,
            cost_dice=dice_weight,
            num_points=cfg.MODEL.MASK_FORMER.TRAIN_NUM_POINTS,
        )

        weight_dict = {"loss_ce": class_weight, "loss_mask": mask_weight, "loss_dice": dice_weight}

        if deep_supervision:
            dec_layers = cfg.MODEL.MASK_FORMER.DEC_LAYERS
            aux_weight_dict = {}
            for i in range(dec_layers - 1):
                aux_weight_dict.update({k + f"_{i}": v for k, v in weight_dict.items()})
            weight_dict.update(aux_weight_dict)

        losses = ["labels", "masks"]

        criterion = SetCriterion(
            sem_seg_head.num_classes,
            matcher=matcher,
            weight_dict=weight_dict,
            eos_coef=no_object_weight,
            losses=losses,
            num_points=cfg.MODEL.MASK_FORMER.TRAIN_NUM_POINTS,
            oversample_ratio=cfg.MODEL.MASK_FORMER.OVERSAMPLE_RATIO,
            importance_sample_ratio=cfg.MODEL.MASK_FORMER.IMPORTANCE_SAMPLE_RATIO,
        )

        return {
            "backbone": backbone,
            "sem_seg_head": sem_seg_head,
            "criterion": criterion,
            "num_queries": cfg.MODEL.MASK_FORMER.NUM_OBJECT_QUERIES,
            "object_mask_threshold": cfg.MODEL.MASK_FORMER.TEST.OBJECT_MASK_THRESHOLD,
            "overlap_threshold": cfg.MODEL.MASK_FORMER.TEST.OVERLAP_THRESHOLD,
            "metadata": MetadataCatalog.get(cfg.DATASETS.TRAIN[0]),
            "size_divisibility": cfg.MODEL.MASK_FORMER.SIZE_DIVISIBILITY,
            "sem_seg_postprocess_before_inference": (
                cfg.MODEL.MASK_FORMER.TEST.SEM_SEG_POSTPROCESSING_BEFORE_INFERENCE
                or cfg.MODEL.MASK_FORMER.TEST.PANOPTIC_ON
                or cfg.MODEL.MASK_FORMER.TEST.INSTANCE_ON
            ),
            "pixel_mean": cfg.MODEL.PIXEL_MEAN,
            "pixel_std": cfg.MODEL.PIXEL_STD,
            # inference
            "semantic_on": cfg.MODEL.MASK_FORMER.TEST.SEMANTIC_ON,
            "instance_on": cfg.MODEL.MASK_FORMER.TEST.INSTANCE_ON,
            "panoptic_on": cfg.MODEL.MASK_FORMER.TEST.PANOPTIC_ON,
            "test_topk_per_image": cfg.TEST.DETECTIONS_PER_IMAGE,
        }