Compute regression and classification targets for one sample. Outputs from a single decoder layer of a single feature level are used.

Private function to load bounding box annotations. The only difference is it remove the proceess for `ignore_flag` Args:

Private function to load label annotations. Args: results (dict): Result dict from :obj :obj:`mmcv.BaseDataset`. Returns

Adds this line to the visualizer.

Adds this line to the visualizer.

Convert results list to `Det3DDataSample`. Subclasses could override it to be compatible for some multi-modality 3D detectors.

Convert results list to `Det3DDataSample`. Subclasses could override it to be compatible for some multi-modality 3D detectors.

Convert results list to `Det3DDataSample`. Subclasses could override it to be compatible for some multi-modality 3D detectors.

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

Wrapper function for data-type agnostic processing. First converts input arrays to PyTorch tensors or NumPy arrays for middle calculation, th

Outer wrapper for the function.

Convert detection results to a list of numpy arrays. Args: bboxes (torch.Tensor): Bounding boxes with shape (N, 5). labels (torch

Convert a list of bounding boxes to roi format. Args: bbox_list (list[torch.Tensor]): A list of bounding boxes corresponding

Map bboxes from testing scale to original image scale. Args: bboxes (:obj:`BaseInstance3DBoxes`): Boxes to be mapped back. scale_

Tensor: BEV of the points in shape (N, 2).

Tensor: BEV of the points in shape (N, 2).

Tensor: 2D BEV box of each box with rotation in XYWHR format, in shape (N, 5).

Tensor: A tensor with center of each box in shape (N, 3).

Tensor: A vector with bottom height of each box in shape (N, ).

Convert box2d to corner. Args: boxes (np.ndarray, shape=[N, 5]): Boxes2d with rotation. Returns: box_corners (np.ndarray, sh

Convert box3d in camera coordinates to bbox in image coordinates. Args: box3d (np.ndarray, shape=[N, 7]): Boxes in camera coordinate.

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

Convert kitti center boxes to corners. 7 -------- 4 /| /| 6 -------- 5 . | | | | . 3 -------- 0

Calculate the center of all the boxes. Note: In MMDetection3D's convention, the bottom center is usually taken as the

Clear the statistics of visible labels.

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

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

Tensor or None: Returns a vector with color of each point in shape (N, 3).

Compute the metrics from processed results. Args: results (list): The processed results of each batch. Returns:

Compute the metrics from processed results after all batches have been processed. Args: results (list): The processed res

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

Convert SparseTensor to pytorch tensor. Args: batch_inputs_dict (dict): The model input dict which includes 'poin

Convert self to ``dst`` mode. Args: dst (int): The target Point mode. rt_mat (Tensor or np.ndarray, optional): The ro

Convert self to ``dst`` mode. Args: dst (int): The target Point mode. rt_mat (Tensor or np.ndarray, optional): The ro

Convert self to ``dst`` mode. Args: dst (int): The target Point mode. rt_mat (Tensor or np.ndarray, optional): The ro

Convert self to ``dst`` mode. Args: dst (:obj:`Box3DMode`): The target Box mode. rt_mat (np.ndarray | torch.Tensor, o

Convert self to ``dst`` mode. Args: dst (int): The target Box mode. rt_mat (Tensor or np.ndarray, optional): The rota

Tensor: Coordinates of each point in shape (N, 3).

Convert boxes_corner to aligned (min-max) boxes. Args: boxes_corner (np.ndarray, shape=[N, 2**dim, dim]): Boxes corners. Returns:

torch.Tensor: Coordinates of corners of all the boxes in shape (N, 8, 3). Convert the boxes to corners in clockwise order, in form of

torch.Tensor: Coordinates of corners of all the boxes in shape (N, 8, 3). Convert the boxes to corners in clockwise order, in form of

Tensor: A tensor with 8 corners of each box in shape (N, 8, 3).

Count the number of scenes.

Create anchors 3d by range. Args: feature_size (list[float] | tuple[float]): Feature map size. It is either a list of a tuple

Convert current boxes to cuda device. Returns: :obj:`BaseInstance3DBoxes`: A new boxes object on the cuda device.

Convert depth map to points in lidar coordinate. Args: depth (np.array, shape=[H, W]): Depth map which the row of [0~`trunc_p

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

Tensor: Size dimensions of each box in shape (N, 3).

Tensor: Size dimensions of each box in shape (N, 3).

Evaluate the model performance of the whole dataset after processing all batches. Args: size (int): Length of the entire

Evaluate the model performance of the whole dataset after processing all batches. Args: size (int): Length of the entire

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

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

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

Flip the boxes along the corresponding axis. Args: direction (str, optional): Flip axis. Defaults to 'X'.

Flip the boxes in BEV along given BEV direction. In Depth coordinates, it flips x (horizontal) or y (vertical) axis. Args:

Flip the boxes in BEV along given BEV direction. Args: bev_direction (str): Direction by which to flip. Can be chosen from

Forward pass. Args: x (list[Tensor]): Features from the backbone. Returns: Tuple[List[Tensor], ...]: Predict

Forward function.

Forward function. Args: x (torch.Tensor): of shape (N, C_in, N_x, N_y, N_z). Returns: list[torch.Tensor]: of

Forward pass of ResNet. Args: x (ME.SparseTensor): Input sparse tensor. Returns: list[ME.SparseTensor]: Outp

Forward function. Args: visual_feat (Tensor): Visual features. # (b, num_query, dim) text_feat (Tensor): Text featur

Forward function. Args: hidden_states (Tensor): Hidden states output from each decoder layer, has shape (num_deco

Forward pass. Args: x (list[Tensor]): Features from the backbone. Returns: Tuple[List[Tensor], ...]: Predict

Forward pass. Args: x (list[Tensor]): Features from the backbone. Returns: Tuple[List[Tensor], ...]: Predict

Convert kitti points(N, >=3) to voxels. Args: points (torch.Tensor): [N, ndim]. Points[:, :3] contain xyz points

convert kitti points(N, >=3) to voxels. Args: feats (torch.Tensor): [N, C]. Points features to be reduced into vo

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

Perform normalization, padding and bgr2rgb conversion based on ``BaseDataPreprocessor``. Args: data (dict or List[dict]):

Forward pass, xyz is (B, N, 3or6), output (B, N, F).

Implements decoder layer in Grounding DINO transformer. Args: query (Tensor): The input query, has shape (bs, num_queries, dim).

Forward function of Transformer decoder. Args: query (Tensor): The input query, has shape (num_queries, bs, dim). val

Forward function. Args: img_feats (List[Tensor]): Image features. pts: (List[Tensor]): A batch of points with shape N

Forward function of loss calculation. Args: source (Tensor): Source set with shape [B, N, C] to calculate Chamfer

Forward function of loss calculation. Args: source (Tensor): Source bbox set with shape [N, bbox_dim] to calculat

Forward function of loss calculation. Args: pred (Tensor): Bbox predictions with shape [..., 7] (x, y, z, w, l, h

torch.Tensor: Coordinates of corners of all the boxes in shape (N, 8, 3). Convert the boxes to corners in clockwise order, in form of

Get the projection matrix of lidar2img. Args: cam2img (torch.Tensor): A 3x3 or 4x4 projection matrix. lidar2cam (torch.Tensor): A

torch.Tensor: A tensor with center of each box in shape (N, 3).

Tensor: A tensor with center of each box in shape (N, 3).

Tensor or None: Returns a vector with height of each point in shape (N, ).

Tensor: A vector with height of each box in shape (N, ).

Calculate height overlaps of two boxes. Note: This function calculates the height overlaps between ``boxes1`` and ``b

Check whether the boxes are in the given range. Args: box_range (Tensor or np.ndarray or Sequence[float]): The range of

Check whether the points are in the given range. Args: point_range (Tensor or np.ndarray or Sequence[float]): The range of

Check whether the boxes are in the given range. Args: box_range (Tensor or np.ndarray or Sequence[float]): The range of

Initialize weights.

Initialize weights.

Initialize weights of the Deformable DETR head.

Initialize weights.

Initialize weights.

Calculate box iou. Note that jit version runs ~10x faster than the box_overlaps function in mmdet3d.core.evaluation. Note: This funct

Limit the yaw to a given period and offset. Args: offset (float): The offset of the yaw. Defaults to 0.5. period (flo

List all the camera frames in the scene. Args: scene (str): Scene name. Returns: list[str] or None: List of

List the categories involved in the dataset.

List all the instance annotations in the scene. Args: scene (str): Scene name. Returns: list[dict] or None: