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

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

Clone the Points. Returns: :obj:`BasePoints`: Box object with the same properties \ as self.

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

Build loss function.

str: The device of the points are on.

Flip the points in BEV along given BEV direction.

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

Translate points with the given translation vector. Args: trans_vector (np.ndarray, torch.Tensor): Translation ve

Build head.

Convert action.

Compute loss. Args: bbox_preds (dict): Predictions from forward of vote head. points (list[torch.Tensor]): Input poin

Initialization before data preparation. Args: results (dict): Dict before data preprocessing. - img_fields (lis

Decode predicted parts to bbox3d. Args: bbox_out (dict): Predictions from model, should contain keys below. - ce

Forward. Args: k (int): number of nearest neighbors. xyz (Tensor): (B, N, 3) if transposed == False, else (B, 3, N).

Generate bboxes from vote head predictions. Args: points (torch.Tensor): Input points. bbox_preds (dict): Predictions

Shuffle the points. Returns: torch.Tensor: The shuffled index.

Training forward function. Args: points (list[torch.Tensor]): Point cloud of each sample. img_metas (list[dict]): Met

Results visualization. Args: results (list[dict]): List of bounding boxes results. out_dir (str): Output directory of

Build detector.

Convert points from `src` mode to `dst` mode. Args: point (tuple | list | np.ndarray | torch.Tensor | BasePoints)

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

Make sparse convolution module. Args: in_channels (int): the number of input channels out_channels (int): the number of out chann

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

Convert multi-modality detection results into 2D results. Project the predicted 3D bbox to 2D image plane and visualize them. Args:

Computes one-to-one matching based on the weighted costs. This method assign each query prediction to a ground truth or background. Th

Build backbone.

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

Get annotation info according to the given index. Args: index (int): Index of the annotation data to get. Returns:

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

torch.Shape: Shape of points.

Test function without augmentaiton.

A function warpper for building 3D detector or segmentor according to cfg. Should be deprecated in the future.

Build PointNet2 set abstraction (SA) module. Args: cfg (None or dict): The SA module config, which should contain: - type (st

Extract features from points.

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataloade

Convert boxes from `src` mode to `dst` mode. Args: box (tuple | list | np.ndarray | torch.Tensor | BaseInstance3D

Find the box which the points are in. Args: points (torch.Tensor): Points in shape (N, 3). Returns: torch.Te

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

Convert a rotated boxes in XYWHR format to XYXYR format. Args: boxes_xywhr (torch.Tensor): Rotated boxes in XYWHR format. Returns:

Randomly get another item with the same flag. Returns: int: Another index of item with the same flag.

Convert instance masks to axis-aligned bounding boxes. Args: points (np.array): Scene points of shape (n, 6). pts_ins

Get the type and mode of box structure. Args: box_type (str): The type of box structure. The valid value are "LiDAR", "Camera

Initialize a model from config file, which could be a 3D detector or a 3D segmentor. Args: config (str or :obj:`mmcv.Config`): Config

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

Build neck.

Format the results to json (standard format for COCO evaluation). Args: results (list[tuple | numpy.ndarray]): Testing results o

KITTI evaluation. Args: gt_annos (list[dict]): Contain gt information of each sample. dt_annos (list[dict]): Contain detected inf

Results visualization. Args: results (list[dict]): List of bounding boxes results. out_dir (str): Output directory

Convert results into format that is directly readable for meshlab. Args: points (np.ndarray): Points. gt_bboxes (np.ndarray): Gro

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

Get root logger and add a keyword filter to it. The logger will be initialized if it has not been initialized. By default a StreamHandler wil

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

Rotate points by angles according to axis. Args: points (torch.Tensor): Points of shape (N, M, 3). angles (torch.Tensor): Vector

Show result by meshlab. Args: data (dict): Contain data from pipeline. result (dict): Predicted result from model. out_di

Grab configs necessary to create a detector. These are deep copied to allow for safe modification of parameters without influencing other tes

Encode ground truth to prediction targets. Args: gt_bboxes_3d (BaseInstance3DBoxes): Ground truth bboxes \ with s

Evaluation in Lyft protocol. Args: results (list[dict]): Testing results of the dataset. metric (str | list[str]): Me

Extract and return the data corresponding to key in result dict. ``results`` is a dict output from `pipeline(input_dict)`, which is the l

Args: input: NC points

Check whether the points are in the given range. Args: point_range (list | torch.Tensor): The range of point (x_m

Merge augmented detection 3D bboxes and scores. Args: aug_results (list[dict]): The dict of detection results. The dict conta

Create a new point object with data. The new point and its tensor has the similar properties \ as self and self.tensor, respectiv

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

Initialization before data preparation. Args: results (dict): Dict before data preprocessing. - img_fields (list

Load data using input pipeline and extract data according to key. Args: index (int): Index for accessing the target data.

Get data loading pipeline in self.show/evaluate function. Args: pipeline (list[dict] | None): Input pipeline. If None is given, \

Decode bboxes. Args: all_cls_scores (Tensor): Outputs from the classification head, \ shape [nb_dec, bs, num_query

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

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

Compute semantic segmentation loss. Args: seg_logit (torch.Tensor): Predicted per-point segmentation logits \ of

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

Training data preparation. Args: index (int): Index for accessing the target data. Returns: dict: Training d

Run semantic segmentation on a single numpy image in form (h, w, 3) where it is uint8 0-255

Generate targets for primitive z and primitive xy. Args: point_mask (torch.Tensor): Tensor to store the ground tr

Create reduced point clouds for given info. Args: data_path (str): Path of original data. info_path (str): Path of data info.

Create reduced point clouds for given info. Args: data_path (str): Path of original data. info_path (str): Path of data info.