Class Pack3DDetInputs

embodiedscan/datasets/transforms/formatting.py:48–291

@TRANSFORMS.register_module()
class Pack3DDetInputs(BaseTransform):
    INPUTS_KEYS = ['points', 'img']
    # to be compatible with depths in bevdepth
    INSTANCEDATA_3D_KEYS = [
        'gt_bboxes_3d', 'gt_labels_3d', 'attr_labels', 'depths', 'centers_2d'
    ]
    INSTANCEDATA_2D_KEYS = [
        'gt_bboxes',
        'gt_bboxes_labels',
    ]

    SEG_KEYS = [
        'gt_seg_map', 'pts_instance_mask', 'pts_semantic_mask',
        'gt_semantic_seg'
    ]

    def __init__(
        self,
        keys: dict,
        meta_keys: dict = (
            'img_path', 'ori_shape', 'img_shape', 'lidar2img', 'depth2img',
            'cam2img', 'pad_shape', 'depth_map_path', 'scale_factor', 'flip',
            'pcd_horizontal_flip', 'pcd_vertical_flip', 'box_mode_3d',
            'box_type_3d', 'img_norm_cfg', 'num_pts_feats', 'pcd_trans',
            'sample_idx', 'pcd_scale_factor', 'pcd_rotation',
            'pcd_rotation_angle', 'lidar_path', 'transformation_3d_flow',
            'trans_mat', 'affine_aug', 'sweep_img_metas', 'ori_cam2img',
            'cam2global', 'crop_offset', 'img_crop_offset', 'resize_img_shape',
            'lidar2cam', 'ori_lidar2img', 'num_ref_frames', 'num_views',
            'ego2global', 'fov_ori2aug', 'ego2cam', 'axis_align_matrix',
            'text', 'tokens_positive', 'scan_id')):
        self.keys = keys
        self.meta_keys = meta_keys

    def _remove_prefix(self, key: str) -> str:
        if key.startswith('gt_'):
            key = key[3:]
        return key

    def transform(self, results: Union[dict,
                                       List[dict]]) -> Union[dict, List[dict]]:
        """Method to pack the input data. when the value in this dict is a
        list, it usually is in Augmentations Testing.

        Args:
            results (dict | list[dict]): Result dict from the data pipeline.

        Returns:
            dict | List[dict]:

            - 'inputs' (dict): The forward data of models. It usually contains
              following keys:

                - points
                - img

            - 'data_samples' (:obj:`Det3DDataSample`): The annotation info of
              the sample.