Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

Access the individual image in its original size. Args: idx: int or slice Returns: Tensor: an image

Args: cfg (CfgNode): model (GeneralizedRCNN): a GeneralizedRCNN to apply TTA on. tta_mapper (callable): t

configurable is experimental.

Args: size (int): the total number of data of the underlying dataset to sample from

NOTE: 'configurable' interface is experimental. Args: is_train: whether it's used in training or inference a

Arguments: tensor (Tensor): of shape (N, H, W) or (N, C_1, ..., C_K, H, W) where K >= 1 image_sizes (list[tuple[int,

Initialize a Pose with Quaternion and 3D Position Parameters ---------- wxyz: np.float32 or Quaternion (default: np.float32([

Left-multiply Pose with another Pose or 3D-Points. Parameters ---------- other: Pose or np.ndarray 1. Pose: Ident