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

Forward pass per level. Args: x (SparseTensor): Per level neck output tensor. Returns: tuple[Tensor]: Per le

Forward pass per level. Args: x (SparseTensor): Per level neck output tensor. scale (mmcv.cnn.Scale): Per level multi

Forward pass per level. Args: x (SparseTensor): Per level neck output tensor. scale (mmcv.cnn.Scale): Per level multi

Get axis_align_matrix from info. If not exist, return identity mat. Args: info (dict): Info of a single sample data. Ret

Get axis_align_matrix from info. If not exist, return identity mat. Args: info (dict): Info of a single sample data. Ret

Compute point centerness w.r.t containing box. Args: face_distances (Tensor): Face distances of shape (B, N, 6),

Compute point centerness w.r.t containing box. Args: face_distances (Tensor): Face distances of shape (B, N, 6),

Calculate distances from point to box faces. Args: points (Tensor): Final locations of shape (N_points, N_boxes, 3).

Calculate distances from point to box faces. Args: points (Tensor): Final locations of shape (N_points, N_boxes, 3).

Get the pad_shape of each image based on data and pad_size_divisor.

Change visible_instance_ids to visible_instance_masks.

Initialize layers. Args: in_channels (tuple[int]): Number of channels in input tensors. out_channels (int): Number of

Initialize classification branch and regression branch of head.

Initialize layers. Args: in_channels (tuple[int]): Number of channels in input tensors. out_channels (int): Number of

Initialize layers. Args: in_channels (tuple[int]): Number of channels in input tensors. out_channels (int): Number of

Initialize layers except for backbone, neck and bbox_head.

Initialize self_attn, cross-attn, ffn, and norms.

Initialize decoder layers.

Check if any points are in the box. Args: box (open3d.geometry.OrientedBoundingBox): Oriented Box. point (np.ndarray)

Check whether to augment based on sr3d utterance.

Private function to load label annotations. Args: results (dict): Result dict from :obj:`mmdet3d.CustomDataset`. Returns

Private function to move the 3D bounding box annotation from `ann_info` field to the root of `results`. Args: results (di

Private function to load 2.5D bounding box annotations. Args: results (dict): Result dict from :obj:`mmdet3d.CustomDataset`.

Private function to load label annotations. Args: results (dict): Result dict from :obj:`mmdet3d.CustomDataset`. Returns

Private function to load 3D mask annotations. Args: results (dict): Result dict from :obj:`mmdet3d.CustomDataset`. Retur

Private function to move the 3D bounding box annotation from `ann_info` field to the root of `results`. Args: results (di

Private function to load 3D panoptic segmentation annotations. Args: results (dict): Result dict from :obj:`mmdet3d.CustomDataset

Private function to load 3D semantic segmentation annotations. Args: results (dict): Result dict from :obj:`mmdet3d.CustomDataset

Private function to move the 3D bounding box annotation from `ann_info` field to the root of `results`. Args: results (di

Private function to move the 3D bounding box annotation from `ann_info` field to the root of `results`. Args: results (di

Loss function of single sample. Args: center_preds (list[Tensor]): Centerness predictions for all levels. bbox_preds

Loss function of single sample. Args: center_preds (list[Tensor]): Centerness predictions for all levels. bbox_preds

Construct Conv-Norm-Act block. Args: in_channels (int): Number of input channels. out_channels (int): Number of outpu

Make a convolutional block. Args: in_channels (int): Number of input channels. out_channels (int): Number of output c

Construct Conv-Norm-Act block. Args: in_channels (int): Number of input channels. out_channels (int): Number of outpu

Construct Conv-Norm-Act block. Args: in_channels (int): Number of input channels. out_channels (int): Number of outpu

Construct DeConv-Norm-Act-Conv-Norm-Act block. Args: in_channels (int): Number of input channels. out_channels (int):

Make a layer from several residual blocks. Args: stride (int): Stride of the first residual block. n_channels (int):

Make single level of residual blocks. Args: block (BasicBlock | Bottleneck): Residual block class. planes (int): Numb

Construct DeConv-Norm-Act-Conv-Norm-Act block. Args: in_channels (int): Number of input channels. out_channels (int):

Make upsampling convolutional block. Args: in_channels (int): Number of input channels. out_channels (int): Number of

Construct DeConv-Norm-Act-Conv-Norm-Act block. Args: in_channels (int): Number of input channels. out_channels (int):

Construct DeConv-Norm-Act-Conv-Norm-Act block. Args: in_channels (int): Number of input channels. out_channels (int):

Args: cls_pred (Tensor): Predicted classification logits. in shape (num_queries, d1, ..., dn), dtype=torch.float3

Args: points (np.ndarray): Input points with shape of (num_points, 3). polygon_surfaces (np.ndarray): Polygon surfaces with shape

Points random sampling. Sample points to a certain number. Args: points (:obj:`BasePoints`): 3D Points. num_

Transform a single image's features extracted from the head into bbox results. Args: cls_score (Tensor): Box score logits

Generate boxes for single sample. Args: center_preds (list[Tensor]): Centerness predictions for all levels. bbox_pred

Generate boxes for single sample. Args: center_preds (list[Tensor]): Centerness predictions for all levels. bbox_pred

Prunes the tensor by score thresholding. Args: x (SparseTensor): Tensor to be pruned. scores (SparseTensor): Scores f

Prunes the tensor by score thresholding. Args: x (SparseTensor): Tensor to be pruned. scores (SparseTensor): Scores f

Prunes the tensor by score thresholding. Args: x (SparseTensor): Tensor to be pruned. scores (SparseTensor): Scores f

Private function to randomly set the scale factor. Args: input_dict (dict): Result dict from loading pipeline. Returns:

Private function to rotate bounding boxes and points. Args: input_dict (dict): Result dict from loading pipeline. Return

Private function to scale bounding boxes and points. Args: input_dict (dict): Result dict from loading pipeline. Returns

Multi-class nms for a single scene. Args: bboxes (Tensor): Predicted boxes of shape (N_boxes, 6) or (N_boxes, 7).

Multi-class nms for a single scene. Args: bboxes (Tensor): Predicted boxes of shape (N_boxes, 6) or (N_boxes, 7).

Private function to translate bounding boxes and points. Args: input_dict (dict): Result dict from loading pipeline. Ret

TODO.

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.

Aligns vector a to vector b with axis angle rotation.

Aligns vector a to vector b with axis angle rotation.

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

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

Calculate overlap between two set of axis aligned 3D bboxes. If ``is_aligned`` is ``False``, then calculate the overlaps between each bbox of

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

Calculate 3D IoU using cuda implementation. Note: This function calculates the IoU of 3D boxes based on their volumes. IoU calcul

Calculate nearest 3D IoU. Note: This function first finds the nearest 2D boxes in bird eye view (BEV), and then calculates the 2D

Some preparations before starting the rendering.

Some preparations before starting the rendering.

Some preparations before starting the rendering.

Center to minmax. Args: centers (np.ndarray): Center points. dims (np.ndarray): Dimensions. origin (list or array or floa

Copy data to the target device and perform normalization, padding and bgr2rgb conversion and stack based on ``BaseDataPreprocessor``.

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

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

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

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

Loss function about feature. Args: feats (list[list[Tensor]]): Feats for all scenes. The first list contains pred

convert 3d box corners from corner function above to surfaces that normal vectors all direct to internal. Args: corners (np.ndarray):

Convert 3d box corners from corner function above to surfaces that normal vectors all direct to internal. Args: corners (np.ndarray):

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

construct a map such that positive_map[i,j] = True if box i is associated to token j Args: tokenized: The tokenized input

Decompress the RGB image data.

Decompress the depth data.

Convert depth map to points. Args: depth (np.array, shape=[H, W]): Depth map which the row of [0~`trunc_pixel`] are truncated

Draw 3D boxes on the image. Args: box (open3d.geometry.OrientedBoundingBox): Box to be drawn. color (tuple): Box colo

Render the next frame. Args: vis (open3d.visualization.VisualizerWithKeyCallback): Visualizer.

Render the next frame. Args: vis (open3d.visualization.VisualizerWithKeyCallback): Visualizer.

Render the next frame. Args: vis (open3d.visualization.VisualizerWithKeyCallback): Visualizer.

Draw the category text on the image. Args: text (str): Text to be drawn. font (cv2.FONT_TYPE): The font type to be us