def __call__()

in mask2former/data/dataset_mappers/mask_former_instance_dataset_mapper.py [0:0]

• 62 lines of code
• 16 McCabe index (conditional complexity)

    def __call__(self, dataset_dict):
        """
        Args:
            dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format.

        Returns:
            dict: a format that builtin models in detectron2 accept
        """
        assert self.is_train, "MaskFormerPanopticDatasetMapper should only be used for training!"

        dataset_dict = copy.deepcopy(dataset_dict)  # it will be modified by code below
        image = utils.read_image(dataset_dict["file_name"], format=self.img_format)
        utils.check_image_size(dataset_dict, image)

        aug_input = T.AugInput(image)
        aug_input, transforms = T.apply_transform_gens(self.tfm_gens, aug_input)
        image = aug_input.image

        # transform instnace masks
        assert "annotations" in dataset_dict
        for anno in dataset_dict["annotations"]:
            anno.pop("keypoints", None)

        annos = [
            utils.transform_instance_annotations(obj, transforms, image.shape[:2])
            for obj in dataset_dict.pop("annotations")
            if obj.get("iscrowd", 0) == 0
        ]

        if len(annos):
            assert "segmentation" in annos[0]
        segms = [obj["segmentation"] for obj in annos]
        masks = []
        for segm in segms:
            if isinstance(segm, list):
                # polygon
                masks.append(polygons_to_bitmask(segm, *image.shape[:2]))
            elif isinstance(segm, dict):
                # COCO RLE
                masks.append(mask_util.decode(segm))
            elif isinstance(segm, np.ndarray):
                assert segm.ndim == 2, "Expect segmentation of 2 dimensions, got {}.".format(
                    segm.ndim
                )
                # mask array
                masks.append(segm)
            else:
                raise ValueError(
                    "Cannot convert segmentation of type '{}' to BitMasks!"
                    "Supported types are: polygons as list[list[float] or ndarray],"
                    " COCO-style RLE as a dict, or a binary segmentation mask "
                    " in a 2D numpy array of shape HxW.".format(type(segm))
                )

        # Pad image and segmentation label here!
        image = torch.as_tensor(np.ascontiguousarray(image.transpose(2, 0, 1)))
        masks = [torch.from_numpy(np.ascontiguousarray(x)) for x in masks]

        classes = [int(obj["category_id"]) for obj in annos]
        classes = torch.tensor(classes, dtype=torch.int64)

        if self.size_divisibility > 0:
            image_size = (image.shape[-2], image.shape[-1])
            padding_size = [
                0,
                self.size_divisibility - image_size[1],
                0,
                self.size_divisibility - image_size[0],
            ]
            # pad image
            image = F.pad(image, padding_size, value=128).contiguous()
            # pad mask
            masks = [F.pad(x, padding_size, value=0).contiguous() for x in masks]

        image_shape = (image.shape[-2], image.shape[-1])  # h, w

        # Pytorch's dataloader is efficient on torch.Tensor due to shared-memory,
        # but not efficient on large generic data structures due to the use of pickle & mp.Queue.
        # Therefore it's important to use torch.Tensor.
        dataset_dict["image"] = image

        # Prepare per-category binary masks
        instances = Instances(image_shape)
        instances.gt_classes = classes
        if len(masks) == 0:
            # Some image does not have annotation (all ignored)
            instances.gt_masks = torch.zeros((0, image.shape[-2], image.shape[-1]))
        else:
            masks = BitMasks(torch.stack(masks))
            instances.gt_masks = masks.tensor

        dataset_dict["instances"] = instances

        return dataset_dict