Construct a shapely Polygon object out of a polygon token. :param polygon_token: The token of the polygon record. :return: Th

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

Returns: bool: whether the field called `name` exists.

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

Start running. Args: data_loaders (list[:obj:`DataLoader`]): Dataloaders for training and validation.

Set the field named `name` to `value`. The length of `value` must be the number of instances, and must agree with other exist

Pillar Feature Net Layer. The Pillar Feature Net could be composed of a series of these layers, but the PointPillars paper results on

Pillar Feature Net Layer. The Pillar Feature Net could be composed of a series of these layers, but the PointPillars paper results on

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

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

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

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

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

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

Initialize conv layers as a prediction branch.

Same as torchvision.ops.boxes.batched_nms, but with float().

Extract features of multiple samples.

Args: tensors: a tuple or list of `torch.Tensor`, each of shape (Hi, Wi) or (C_1, ..., C_K, Hi, Wi) where K >= 1.

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

nn.Module: normalization layer after the first convolution layer

Args: boxes (Boxes, RotatedBoxes or ndarray): either a :class:`Boxes`, or an Nx4 numpy array of XYXY_ABS format f

Args: config_path: relative config filename

Apply dynamic voxelization to points. Args: points (list[torch.Tensor]): Points of each sample. Returns: tup

Set random seed. Args: seed (int): Seed to be used. deterministic (bool): Whether to set the deterministic option for

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

Args: input_ch(int) : the number of input channel out_features (list[str]): name of the layers whose outputs should

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]): Input pipeline. If None is given,

Build RoI feature extractor.

Get radius of gaussian. Args: det_size (tuple[torch.Tensor]): Size of the detection result. min_overlap (float, optional): Gaussi

Args: norm (str or callable): either one of BN, SyncBN, FrozenBN, GN; or a callable that takes a channel number and returns

query_bbox: [B, Q, 10] offset: [B, Q, num_points, 4], normalized by stride

nn.Module: normalization layer after the second convolution layer

Given two lists of boxes of size N and M, compute the IoU (intersection over union) between **all** N x M pairs of boxes. The box order m

Find all boxes in which each point is. Args: points (torch.Tensor): Points in shape (1, M, 3) or (M, 3), 3 dimens

Args: input_ch(int) : the number of input channel out_features (list[str]): name of the layers whose outputs should

Adds a list of boxes.

Apply transformation `deltas` (dx, dy, dw, dh) to `boxes`. Args: deltas (Tensor): transformation deltas of shape (N, k*4

Computes the area of all the boxes. Returns: torch.Tensor: a vector with areas of each box.

Calculate the ious between each bbox of bboxes1 and bboxes2. Args: bboxes1 (ndarray): Shape (n, 4) bboxes2 (ndarray): Shape (k, 4)

Build detector.

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

Circular NMS. An object is only counted as positive if no other center with a higher confidence exists within a radius r using a bird-eye

Sigmoid function for input feature. Args: x (torch.Tensor): Input feature map with the shape of [B, N, H, W]. eps (float, optiona

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

Args: box: can be a k-tuple, k-list or an Nxk array/tensor, where k = 4 or 5 from_mode, to_mode (BoxMode) Re

Example: >>> from mmdet.models.roi_heads.mask_heads.fcn_mask_head import * # NOQA >>> N = 7 # N = number of extract

Main function that loads the evaluation code, visualizes samples, runs the evaluation and renders stat plots. :param plot_examples: H

Renders various PR and TP curves. :param metrics: DetectionMetrics instance. :param md_list: DetectionMetricDataList instance

Scale the box with horizontal and vertical scaling factors

Sets the MetricData entry for a certain detection_name and match_distance.

Create configs and perform basic setups.

Transform the coordinates with matrix T. Args: T (np.ndarray): Transformation matrix. x(float): Coordinate in x axis.

Data preparation for voxel pooling. Args: coor (torch.tensor): Coordinate of points in the lidar space in shape (

Args: dim (int): Number of input channels. num_heads (int): Number of attention heads in each ViT block.