def convert_valid_bboxes()

in a2d2/a2d2_dataset.py [0:0]

• 50 lines of code
• 3 McCabe index (conditional complexity)

    def convert_valid_bboxes(self, box_dict, info):
        """Convert the predicted boxes into valid ones.

        Args:
            box_dict (dict): Box dictionaries to be converted.

                - boxes_3d (:obj:`LiDARInstance3DBoxes`): 3D bounding boxes.
                - scores_3d (torch.Tensor): Scores of boxes.
                - labels_3d (torch.Tensor): Class labels of boxes.
            info (dict): Data info.

        Returns:
            dict: Valid predicted boxes.

                - bbox (np.ndarray): 2D bounding boxes.
                - box3d_camera (np.ndarray): 3D bounding boxes in \
                    camera coordinate.
                - box3d_lidar (np.ndarray): 3D bounding boxes in \
                    LiDAR coordinate.
                - scores (np.ndarray): Scores of boxes.
                - label_preds (np.ndarray): Class label predictions.
                - sample_idx (int): Sample index.
        """
        # TODO: refactor this function
        box_preds = box_dict['boxes_3d']
        scores = box_dict['scores_3d']
        labels = box_dict['labels_3d']
        sample_idx = info['image']['image_idx']
        # TODO: remove the hack of yaw
        box_preds.tensor[:, -1] = box_preds.tensor[:, -1] - np.pi
        box_preds.limit_yaw(offset=0.5, period=np.pi * 2)

        if len(box_preds) == 0:
            return dict(
                bbox=np.zeros([0, 4]),
                box3d_camera=np.zeros([0, 7]),
                box3d_lidar=np.zeros([0, 7]),
                scores=np.zeros([0]),
                label_preds=np.zeros([0, 4]),
                sample_idx=sample_idx)

        rect = info['calib']['R0_rect'].astype(np.float32)
        Trv2c = info['calib']['Tr_velo_to_cam'].astype(np.float32)
        P2 = info['calib']['P2'].astype(np.float32)
        img_shape = info['image']['image_shape']
        P2 = box_preds.tensor.new_tensor(P2)

        box_preds_camera = box_preds.convert_to(Box3DMode.CAM, rect @ Trv2c)

        box_corners = box_preds_camera.corners
        box_corners_in_image = points_cam2img(box_corners, P2)
        # box_corners_in_image: [N, 8, 2]
        minxy = torch.min(box_corners_in_image, dim=1)[0]
        maxxy = torch.max(box_corners_in_image, dim=1)[0]
        box_2d_preds = torch.cat([minxy, maxxy], dim=1)
        # Post-processing
        # check box_preds_camera
        image_shape = box_preds.tensor.new_tensor(img_shape)
        valid_cam_inds = ((box_2d_preds[:, 0] < image_shape[1]) &
                          (box_2d_preds[:, 1] < image_shape[0]) &
                          (box_2d_preds[:, 2] > 0) & (box_2d_preds[:, 3] > 0))
        # check box_preds
        limit_range = box_preds.tensor.new_tensor(self.pcd_limit_range)
        valid_pcd_inds = ((box_preds.center > limit_range[:3]) &
                          (box_preds.center < limit_range[3:]))
        valid_inds = valid_cam_inds & valid_pcd_inds.all(-1)

        if valid_inds.sum() > 0:
            return dict(
                bbox=box_2d_preds[valid_inds, :].numpy(),
                box3d_camera=box_preds_camera[valid_inds].tensor.numpy(),
                box3d_lidar=box_preds[valid_inds].tensor.numpy(),
                scores=scores[valid_inds].numpy(),
                label_preds=labels[valid_inds].numpy(),
                sample_idx=sample_idx)
        else:
            return dict(
                bbox=np.zeros([0, 4]),
                box3d_camera=np.zeros([0, 7]),
                box3d_lidar=np.zeros([0, 7]),
                scores=np.zeros([0]),
                label_preds=np.zeros([0, 4]),
                sample_idx=sample_idx)