Concatenate a list of Points into a single Points. Args: points_list (Sequence[:obj:`BasePoints`]): List of points. Retu

Concatenate a list of Boxes into a single Boxes. Args: boxes_list (Sequence[:obj:`BaseInstance3DBoxes`]): List of boxes.

Reload ``numpy`` from self.tensor.

Convert current points to a specific device. Args: device (str or :obj:`torch.device`): The name of the device. Returns:

Convert current points to cpu device. Returns: :obj:`BasePoints`: A new points object on the cpu device.

Load basic information of a given RGBD frame.

Convert objects of various python types to :obj:`torch.Tensor`. Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`, :class:`S

Clone the boxes. Returns: :obj:`BaseInstance3DBoxes`: Box object with the same properties as self.

Clone the points. Returns: :obj:`BasePoints`: Point object with the same properties as self.

Rotate points by angles according to axis. Args: points (np.ndarray | torch.Tensor | list | tuple ): Points of shape (N, M, 3

setattr is only used to set data. The value must have the attribute of `__len__` and have the same length of `PointData`.

Limit the value into a period for periodic function. Args: val (np.ndarray or Tensor): The value to be converted. offset (float):

Rotate points by angles according to axis. Args: points (np.ndarray or Tensor): Points with shape (N, M, 3). angles (np.ndarray o

Draw the camera pose in the form of a cone. Args: camera_pose (numpy.ndarray): 4x4 camera pose from camera to world. camera_size

Get the type and mode of box structure. We temporarily only support EulerDepthInstance3DBoxes to support 9-DoF box operations and will co

Get the color of a given category label. Args: label (str): Category name. Returns: list: RGB value of the m

Obtain image features using points. Args: img_meta (dict): Meta information. coord_type (str): 'DEPTH' or 'CAMERA' or 'LIDAR'. Ca

Convert current boxes to a specific device. Args: device (str or :obj:`torch.device`): The name of the device. Returns:

Convert 9-DoF box from array/tensor to open3d.OrientedBoundingBox. Args: box (numpy.ndarray|torch.Tensor|List[float]): 9-DoF

Batch version of point_sample. Args: img_meta (dict): Meta info. img_features (Tensor): B x C x H x W image features. poi

Convert points from ``src`` mode to ``dst`` mode. Args: box (Sequence[float] or np.ndarray or Tensor or :obj:`BasePoints`):

Flip the points along given BEV direction. Args: bev_direction (str): Flip direction (horizontal or vertical). De

Project points in camera coordinates to image coordinates. Args: points_3d (Tensor or np.ndarray): Points in shape (N, 3). proj_m

Obtain the mean of tensor on different GPUs.

Rotate points with the given rotation matrix or angle. Args: rotation (Tensor or np.ndarray or float): Rotation matrix or angle.

Transform predicted bbox parameters to bbox. Args: points (Tensor): Final locations of shape (N, 3) bbox_pred (Tensor

Calculate Chamfer Distance of two sets. Args: src (Tensor): Source set with shape [B, N, C] to calculate Chamfer Distance.

Detach the points. Returns: :obj:`BasePoints`: Point object with the same properties as self.

Calculate 3D overlaps of two boxes. Note: This function calculates the overlaps between ``boxes1`` and ``boxes2``, ``

Calculate 3D overlaps of two boxes. Note: This function calculates the overlaps between ``boxes1`` and ``boxes2``, ``

Obtain image features using points. Args: img_meta (dict): Meta info. img_features (Tensor): 1 x C x H x W image features.

Transform function to sample points to in indoor scenes. Args: input_dict (dict): Result dict from loading pipeline. Ret

Translate points with the given translation vector. Args: trans_vector (Tensor or np.ndarray): Translation vector of size 3

Convert points in camera coordinate to lidar coordinate. Note: This function is for KITTI only. Args: points (np.ndarray, sh

Convert input array to target data type. Args: input_array (np.ndarray or torch.Tensor or list or tuple or int or

Directly extract features from the backbone+neck. Args: batch_inputs_dict (dict): The model input dict which includes

Extract 3d features from the backbone -> fpn -> 3d projection. -> 3d neck -> bbox_head. Args: batch_inputs_dict (dict):

Directly extract features from the backbone+neck. Args: batch_inputs_dict (dict): The model input dict which includes

Directly extract features from the backbone+neck. Args: batch_inputs_dict (dict): The model input dict which includes

Extract 3d features from the backbone -> fpn -> 3d projection. -> 3d neck -> bbox_head. Args: batch_inputs_dict (dict):

Get the class of points according to coordinate type. Args: points_type (str): The type of points coordinate. The valid value are

Convert the sample index to string.

Reload ``numpy`` from self.tensor.

Method to pack the single input data. when the value in this dict is a list, it usually is in Augmentations Testing. Args:

Save a matrix to file.

Scale the points with horizontal and vertical scaling factors. Args: scale_factors (float): Scale factors to scale the points.

Transform predicted bbox parameters to bbox. Args: points (Tensor): Final locations of shape (N, 3) bbox_pred (Tensor

Remove annotations that do not need to be cared. -1 indicates dontcare in MMDet3d. Args: ann_info (dict): Dict of annota

Generate anchors in a single range. Args: feature_size (list[float] | tuple[float]): Feature map size. It is eith

Apply transformation to input point cloud. Args: pcd (Tensor): The point cloud to be transformed. coord_type (str): 'DEPTH' or 'C

Transform bbox parameters to the 8 corners. Args: bbox (Tensor): 3D box of shape (N, 6) or (N, 7) or (N, 9). Returns: Tensor

Convert kitti locations, dimensions and angles to corners. format: center(xy), dims(xy), angles(counterclockwise when positive) Args:

Convert kitti locations, dimensions and angles to corners. Args: centers (np.ndarray): Locations in kitti label file with shape (N, 3).

Close the visualizer. Args: vis (open3d.visualization.VisualizerWithKeyCallback): Visualizer.

Convert boxes from ``src`` mode to ``dst`` mode. Args: box (Sequence[float] or np.ndarray or Tensor or :obj:`Base

Generate relative box corners based on length per dim and origin point. Args: dims (np.ndarray, shape=[N, ndim]): Array of length per dim

Convert current points to cuda device. Returns: :obj:`BasePoints`: A new points object on the cuda device.

torch.device: The device of the points are on.

torch.device: The device of the boxes are on.

Forward function. Args: mlvl_feats (list[Tensor]): Multi-level features. input_metas (list[dict]): Input meta infos.

Scatters points into voxels. Args: points (torch.Tensor): Points to be reduced into voxels. coors (torch.Tensor): Cor

Geometric scene-class affinity loss. Only consider empty and nonempty probabilities. Args: pred (Tensor): Prediction maps. s

Generate grid anchors in multiple feature levels. Args: featmap_sizes (list[tuple]): List of feature map sizes in

Create a new box object with data. The new box and its tensor has the similar properties as self and self.tensor, respectively.

Produce multi-scale occupancy supervision from ground truth. Args: gt_occ (list[Tensor]): Ground truth occupancy. ratio (int): Do

x_raw, y_raw: both tensors (batch, 3).

x_raw, y_raw: both tensors batch*3.

Process the `instances` in data info to `ann_info`. Args: info (dict): Info dict. Returns: dict: Processed `

Process the `instances` in data info to `ann_info`. Args: info (dict): Info dict. Returns: dict: Processed `

Parse the package dependencies listed in a requirements file but strips specific versioning information. Args: fname (str): path to r

Project points in image coordinates to camera coordinates. Args: points (Tensor or np.ndarray): 2.5D points in 2D images with shape

Check points is in 3d convex polygons. Args: points (np.ndarray): Input points with shape of (num_points, 3). polygon_surfaces (n

Flip 3D data randomly. `random_flip_data_3d` should take these situations into consideration: - 1. LIDAR-based 3d detection

Set template array. Args: array (np.ndarray or torch.Tensor or list or tuple or int or float): Template array.

Perform normalization, padding and bgr2rgb conversion for img data based on ``BaseDataPreprocessor``, and voxelize point cloud if `voxel`

int: Number of points in the current object.

Args: cls_pred (Tensor): Predicted classification logits, shape (num_queries, num_class). gt_labels (