def __call__()

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

• 43 lines of code
• 11 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
        """
        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)

        if self.crop_gen is None:
            image, transforms = T.apply_transform_gens(self.tfm_gens, image)
        else:
            if np.random.rand() > 0.5:
                image, transforms = T.apply_transform_gens(self.tfm_gens, image)
            else:
                image, transforms = T.apply_transform_gens(
                    self.tfm_gens[:-1] + self.crop_gen + self.tfm_gens[-1:], image
                )

        image_shape = image.shape[:2]  # 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"] = torch.as_tensor(np.ascontiguousarray(image.transpose(2, 0, 1)))

        if not self.is_train:
            # USER: Modify this if you want to keep them for some reason.
            dataset_dict.pop("annotations", None)
            return dataset_dict

        if "pan_seg_file_name" in dataset_dict:
            pan_seg_gt = utils.read_image(dataset_dict.pop("pan_seg_file_name"), "RGB")
            segments_info = dataset_dict["segments_info"]

            # apply the same transformation to panoptic segmentation
            pan_seg_gt = transforms.apply_segmentation(pan_seg_gt)

            from panopticapi.utils import rgb2id

            pan_seg_gt = rgb2id(pan_seg_gt)

            instances = Instances(image_shape)
            classes = []
            masks = []
            for segment_info in segments_info:
                class_id = segment_info["category_id"]
                if not segment_info["iscrowd"]:
                    classes.append(class_id)
                    masks.append(pan_seg_gt == segment_info["id"])

            classes = np.array(classes)
            instances.gt_classes = torch.tensor(classes, dtype=torch.int64)
            if len(masks) == 0:
                # Some image does not have annotation (all ignored)
                instances.gt_masks = torch.zeros((0, pan_seg_gt.shape[-2], pan_seg_gt.shape[-1]))
            else:
                masks = BitMasks(
                    torch.stack([torch.from_numpy(np.ascontiguousarray(x.copy())) for x in masks])
                )
                instances.gt_masks = masks.tensor

            dataset_dict["instances"] = instances

        return dataset_dict