Perform feature aggregation using pooling operation. Args: features (torch.Tensor): (B, C, N, K) Features of loca

Prepare input point pairs features for self.ScoreNet. Args: points_xyz (torch.Tensor): (B, 3, npoint, K) Coordina

Removes point too close within a certain radius from origin. Args: points (np.ndarray | :obj:`BasePoints`): Sweep points.

Removes point too close within a certain radius from origin. Args: points (np.ndarray | :obj:`BasePoints`): Sweep points.

Rotate 2D boxes. Args: corners (np.ndarray): Corners of boxes. angle (float): Rotation angle. rot_mat_T (np.ndarray): Tra

Perform point sampling based on inputs. If `indices` is specified, directly sample corresponding points. Else if `target_xyz` is spec

Sample points for each points subset. Args: points (np.ndarray): Points subset to be sampled. sampler (VoxelGenerator

Select transform. Args: transform (np.ndarray): Transforms to select from. indices (np.ndarray): Mask to indicate which transform

Set flag according to image aspect ratio. Images with aspect ratio greater than 1 will be set as group 1, otherwise group 0. In 3D da

Split coordinates and features of input points. Args: points (torch.Tensor): Point coordinates with features, wit

Export oriented (around Z axis) scene bbox to meshes. Args: scene_bbox(list[ndarray] or ndarray): xyz pos of center and 3 len

Add bounding box to visualizer. Args: bbox3d (numpy.array, shape=[M, 7]): 3D bbox (x, y, z, dx, dy, dz, yaw) to b

Add segmentation mask to visualizer via per-point colorization. Args: seg_mask_colors (numpy.array, shape=[N, 6]):

Compute regression and classification targets for anchors. Args: anchor_list (list[list]): Multi level anchors of each image.

Test function with augmentation, stage 2. Args: points (list[list[torch.Tensor]], optional): the outer list indic

Calculate average precision (for single or multiple scales). Args: recalls (np.ndarray): Recalls with shape of (num_scales, num_dets) \

Convert 3D detection results to kitti format for evaluation and test submission. Args: net_outputs (list[np.ndarray]): Li

Convert results to kitti format for evaluation and test submission. Args: net_outputs (List[np.ndarray]): list of array storing t

Convert results to kitti format for evaluation and test submission. Args: net_outputs (List[np.ndarray]): list of array storing t

Convert 2D detection results to kitti format for evaluation and test submission. Args: net_outputs (list[np.ndarray]): Li

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

Multi-class weighted nms for 3D boxes, cpu version. Args: mlvl_bboxes (torch.Tensor): Multi-level boxes with shape (N, M). M i

Box collision test. Args: boxes (np.ndarray): Corners of current boxes. qboxes (np.ndarray): Boxes to be avoid colliding.

Build RoI feature extractor.

Build voxel encoder.

Calculating square distance between a and b. Args: point_feat_a (Tensor): (B, N, C) Feature vector of each point. point_feat_b (T

Convert the box from camera to global coordinate. Args: info (dict): Info for a specific sample data, including the calibrati

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

Collect the information of the running environments.

Convert action.

Convert config's naiveSyncBN to BN. Args: config (str or :obj:`mmcv.Config`): Config file path or the config object.

Convert range images to point cloud. Args: frame (:obj:`Frame`): Open dataset frame. range_images (dict): Mapping fro

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

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

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

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

torch.Tensor: a tensor with 8 corners of each box.

Decode center, size residuals and class to corners. Only useful for axis-aligned bounding boxes, so angle isn't considered. Args:

str: The device of the boxes are on.

Enlarge the length, width and height boxes. Args: extra_width (float | torch.Tensor): Extra width to enlarge the box. Re

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

Extract image augmentation information from img_meta. Args: img_meta(dict): Meta info regarding data transformation. tensor(torch

Extract features from points.

Extract features from points.

Extract features from points.

Extract features from points.

Extract features from images and points.

Extract features from points.

Extract 3d features from the backbone -> fpn -> 3d projection. Args: img (torch.Tensor): Input images of shape (N, C_in, H, W).

Extract features from points.

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.

Flip the boxes in BEV along given BEV direction.

Flip the boxes in BEV along given BEV direction.

Flip the boxes in BEV along given BEV direction.

Format the results to pkl file. Args: outputs (list[dict]): Testing results of the dataset. pklfile_prefix (str | Non

Format the results to pkl file. Args: outputs (list[dict]): Testing results of the dataset. pklfile_prefix (str | Non

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

Format the results to json (standard format for COCO evaluation). Args: results (list[dict]): Testing results of the dataset.

Placeholder of forward function.

Calls either simple_test or aug_test depending on the length of outer list of points. If len(points) == 1, call simple_test. Otherwise

During inference, the functionary of batch norm layers is turned off but only the mean and var alone channels are used, which exposes the chance t

Get the 2D annotation records for a given info. Args: info: Information of the given sample data. occluded: Integer (0, 1, 2, 3)

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

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

Get available scenes from the input nuscenes class. Given the raw data, get the information of available scenes for further info generation.

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

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

Encode direction to 0 ~ num_bins-1. Args: anchors (torch.Tensor): Concatenated multi-level anchor. reg_targets (torch.Tensor): Bb

Fast version of get_innner_win_inds_slow Args: win_inds indicates which windows a voxel belongs to. Voxels share a windo

Fast version of get_innner_win_inds_slow Args: win_inds indicates which windows a voxel belongs to. Voxels share a windo

Fast version of get_innner_win_inds_slow Args: win_inds indicates which windows a voxel belongs to. Voxels share a windo

Fast version of get_innner_win_inds_slow Args: win_inds indicates which windows a voxel belongs to. Voxels share a windo

Fast version of get_innner_win_inds_slow Args: win_inds indicates which windows a voxel belongs to. Voxels share a windo

Fast version of get_innner_win_inds_slow Args: win_inds indicates which windows a voxel belongs to. Voxels share a windo

Fast version of get_innner_win_inds_slow Args: win_inds indicates which windows a voxel belongs to. Voxels share a windo

Fast version of get_innner_win_inds_slow Args: win_inds indicates which windows a voxel belongs to. Voxels share a windo

Fast version of get_innner_win_inds_slow Args: win_inds indicates which windows a voxel belongs to. Voxels share a windo