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

Map bboxes from the original image scale to testing scale.

Transform network output for a batch into bbox predictions. Args: cls_scores (list[Tensor]): Box scores for each scale level

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

Initialize conv sequential for CornerHead.

Mask head forward function used in both training and testing.

Assign gt to bboxes. This method assign a gt bbox to every bbox (proposal/anchor), each bbox will be assigned with -1, or a semi-posi

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

Build backbone.

nn.Module: the normalization layer named "norm1"

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

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

Convert masks to the format of ndarray.

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

Box forward function used in both training and testing.

Replace the ImageToTensor transform in a data pipeline to DefaultFormatBundle, which is normally useful in batch inference. Args: pip

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

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

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

Build roi extractor.

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

Extract features from images and points.

Return the class containing the corresponding attributes according to the test_step_names.

Get points according to feature map sizes. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes. img_meta

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``, ``

Apply element-wise weight and reduce loss. Args: loss (Tensor): Element-wise loss. weight (Tensor): Element-wise weights.

Builder of IoU calculator.

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

Training forward function of PartAggregationROIHead. Args: feats_dict (dict): Contains features from the first stage.

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

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

Inference image(s) with the detector. Args: model (nn.Module): The loaded detector. imgs (str/ndarray or list[str/ndarray] or tup

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

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

Convert Mask to ndarray.. Args: mask (:obj:`BitmapMasks` or :obj:`PolygonMasks` or torch.Tensor or np.ndarray): The mask to be co

Merge augmented mask prediction. Args: aug_masks (list[ndarray]): shape (n, #class, h, w) img_shapes (list[ndarray]): shape (3, )

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

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

Regress the bbox for the predicted class. Used in Cascade R-CNN. Args: rois (Tensor): shape (n, 4) or (n, 5) label (T

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

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.

Load a configuration as a python module.

Given feats and indexes, returns the transposed and gathered feats. Args: feat (torch.Tensor): Features to be transposed and gath

Transpose and gather feature according to index. Args: feat (Tensor): Target feature map. ind (Tensor): Target coord

Check whether the anchors are inside the border. Args: flat_anchors (torch.Tensor): Flatten anchors, shape (n, 4). valid_flags (t

Convert bbox coordinates from (cx, cy, w, h) to (x1, y1, x2, y2). Args: bbox (Tensor): Shape (n, 4) for bboxes. Returns: Ten

Builder of IoU calculator.

Calculate Chamfer Distance of two sets. Args: src (torch.Tensor): Source set with shape [B, N, C] to calculate Chamfer Distan

Apply transformation `pred_bboxes` to `boxes`. Args: bboxes (torch.Tensor): Basic boxes. Shape (B, N, 4) or (N, 4) pr

Apply transformation `pred_bboxes` to `boxes`. Args: bboxes (torch.Tensor): Basic boxes.Shape (B, N, 4) or (N, 4) pre

Forward function for image branch. This function works similar to the forward function of Faster R-CNN. Args: x (list[to

Draw bboxes and class labels (with scores) on an image. Args: img (str or ndarray): The image to be displayed. bboxes (ndarray):

Initialize a detector from config file. Args: config (str or :obj:`mmcv.Config`): Config file path or the config object.

Compute loss. Args: bbox_preds (dict): Predictions from forward of h3d bbox head. points (list[torch.Tensor]): Input

make plugins for block. Args: in_channels (int): Input channels of plugin. plugins (list[dict]): List of plugins cfg

Match points to plane. Args: plane (torch.Tensor): Equation of the plane. points (torch.Tensor): Points of input.

nn.Module: normalization layer after the third convolution layer

Obtain image features using points. Args: img_meta (dict): Meta info. img_features (torch.Tensor): 1 x C x H x W image features.

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

Refine bboxes during training. Args: rois (Tensor): Shape (n*bs, 5), where n is image number per GPU, and bs is t

See :func:`BaseInstanceMasks.resize`.

see :func:`BaseInstanceMasks.resize`

Show RPN proposals on the image. Args: data (str or np.ndarray): Image filename or loaded image. result (Tensor or tu

Simple testing forward function of PartAggregationROIHead. Note: This function assumes that the batch size is 1 Args:

Test without augmentation.

Test without augmentation. Args: x (tuple[Tensor]): Features from the upstream network, each is a 4D-tensor.

Box head forward function used in both training and testing.

Create sample results that can be passed to BBoxHead.get_targets.

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

Assign anchors and encode positive anchors. Args: bbox_assigner (BaseAssigner): assign positive and negative boxes. a

Calculate overlap between two set of bboxes. If ``is_aligned `` is ``False``, then calculate the overlaps between each bbox of bboxes1 and bb