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

Build a mask head defined by `cfg.MODEL.ROI_MASK_HEAD.NAME`.

Build a proposal generator from `cfg.MODEL.PROPOSAL_GENERATOR.NAME`. The name can be "PrecomputedProposals" to use no proposal generator.

Create a ResNet instance from config. Returns: ResNet: a :class:`ResNet` instance.

Build a semantic segmentation head from `cfg.MODEL.SEM_SEG_HEAD.NAME`.

Returns: iterable It now calls :func:`detectron2.data.build_detection_train_loader`. Overwrite it if you'd like

Create a VoVNet instance from config. Returns: VoVNet: a :class:`VoVNet` instance.

Calculate the area of the given 2d bbox Input is assumed to be xmin, ymin, xmax, ymax tuple

Takes in all vertices in pixel projection and calculates min and max of all x and y coordinates. Returns left top, right bottom pixel coordin

Spatial Relative Positional Embeddings.

Convert kitti locations, dimensions and angles to corners. format: center(xy), dims(xy), angles(counterclockwise when positive) Args:

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

Plot the true positive curve for the specified class. :param md_list: DetectionMetricDataList instance. :param metrics: DetectionMetrics

Clip (in place) the boxes by limiting x coordinates to the range [0, width] and y coordinates to the range [0, height]. For

Collect the information of the running environments.

Compute planner metric for one sample same as stp3.

1x1 convolution with padding

1x1 convolution with padding

1x1 convolution with padding

3x3 convolution with padding

3x3 convolution with padding

3x3 convolution with padding

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

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

Convert a scripted Instances object to a regular :class:`Instances` object

Generate relative box corners based on length per dim and origin point. Args: dims (np.ndarray, shape=[N, ndim]): Array of length per dim

When a dependency of a class is not available, create a dummy class which throws ImportError when used. Args: klass (str): name

When a dependency of a function is not available, create a dummy function which throws ImportError when used. Args: func (str):

Generate the frustum template for each image. Args: depth_cfg (tuple(float)): Config of grid alone depth axis in format

Computes the cumulative mean up to each position in a NaN sensitive way - If all values are NaN return an array of ones. - If some values

each line with 1 meter width pred_lines: num_preds, List [npts, 2] gt_lines: num_gts, npts, 2 gt_mask: num_gts, npts,

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

Perform some basic common setups at the beginning of a job, including: 1. Set up the detectron2 logger 2. Log basic information about en

Initialize from serialized content.

str: The device of the boxes are on.

Get gaussian masked heatmap. Args: heatmap (torch.Tensor): Heatmap to be masked. center (torch.Tensor): Center coord of the heatm

Project the 3D bbox on 2D plane and draw on input image. Args: bboxes3d (:obj:`LiDARInstance3DBoxes`): 3d bbox in lidar coord

Args: segment: numpy array of shape Nx2, containing all the points in the polygon. color: color of the polygon. Refer

Draw semantic segmentation predictions/labels. Args: sem_seg (Tensor or ndarray): the segmentation of shape (H, W).

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for E

Evaluation in COCO protocol. Args: results (list[list | tuple]): Testing results of the dataset. metric (str | list[s

trajs: torch.Tensor (B, n_future, 2) 自车lidar系为轨迹参考系 ^ y | | 0------->

traj: torch.Tensor (n_future, 2) 自车lidar系为轨迹参考系 ^ y | | 0-------

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 images and points.

Extract features from points.

Extract features from points. Args: points (list[Tensor]): Raw point clouds. Returns: SparseTensor: Voxelize

Extract features from points.

Extract features from images and points. Return: (BEV Feature, None, depth)

Extract features from images and points. Return: (BEV Feature, None, depth)

Extract features from images and points.

Extract features from images and points. Return: (BEV Feature, None, depth)

Extract features from images and points. Return: (BEV Feature, None, depth)

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

Directly extract features from the backbone+neck. Args: points (torch.Tensor): Input points. Returns: dict:

Directly extract features from the backbone+neck. Args: points (torch.Tensor): Input points.

Extract point and image features of multiple samples.

Extract features of images.

Extract features of images.