Call `fast_rcnn_inference_single_image` for all images. Args: boxes (list[Tensor]): A list of Tensors of predicted class-specific or

Single-image inference. Return bounding-box detection results by thresholding on scores and applying non-maximum suppression (NMS). Args

Applies filtering to boxes. basedon overlap . :param nusc: An instance of the NuScenes class. :param eval_boxes: An instance of the EvalB

Applies filtering to boxes. basedon overlap . :param nusc: An instance of the NuScenes class. :param eval_boxes: An instance of the EvalB

Find the latest checkpoint from the working directory. This function is copied from mmdetection. Args: path(str): The path to find ch

Flip the boxes in BEV along given BEV direction. Args: bev_direction (str, optional): Direction by which to flip.

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

Foraward function to scatter features.

Forward function. Args: mlvl_feats (tuple[Tensor]): Features from the upstream network, each is a 5D-tensor with s

Placeholder of forward function.

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

Forward function' Args: pts_feats (list[torch.Tensor]): Features of point cloud branch gt_bboxes_3d (list[:obj:`BaseIn

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

Generate proposals from encoded memory. Args: memory (Tensor) : The output of encoder, has shape (bs, num_key, emb

Generate voxels given points.

r"""NuScenes Dataset. This class serves as the API for experiments on the NuScenes Dataset. Args: coors (Nx2): coordinates of valid

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

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

Calculate absolute positional embeddings. If needed, resize embeddings and remove cls_token dimension for the original embeddings. Ar

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.

Get the bounds of the geometric object that corresponds to a non geometric record. :param layer_name: Name of the layer that we are i

Get COCO category ids by index. Args: idx (int): Index of data. Returns: list[int]: All categories in the im

Returns: The box centers in a Nx2 array of (x, y).

Returns the URL to the model trained using the given config Args: config_path (str): config file name relative to detectron2's "conf

Get class names of current dataset. Args: classes (Sequence[str] | str): If classes is None, use default CLASSES

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

Get box regression transformation deltas (dx, dy, dw, dh) that can be used to transform the `src_boxes` into the `target_boxes`. That

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

Encode direction to 0 ~ num_bins-1. Args: reg_targets (torch.Tensor): Bbox regression targets. dir_offset (int, optio

Determine the (x,y,z) locations (in the ego frame) of the points in the point cloud. Returns B x N x D x H/downsample x W/downsample x

Determine the (x,y,z) locations (in the ego frame) of the points in the point cloud. Returns B x N x D x H/downsample x W/downsample x

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

Calculate the locations of the frustum points in the lidar coordinate system. Args: rots (torch.Tensor): Rotation from ca

Calculate loss of voting module. Args: seed_points (torch.Tensor): Coordinate of the seed points. vote_points (torch.

Create boolean mask by actually number of a padded tensor. Args: actual_num (torch.Tensor): Actual number of points in each voxel.

Decode box predictions and get projected 2D attributes. Args: bbox_preds (list[Tensor]): Box predictions for each scale

Get all the record token that intersects or is within a particular rectangular patch. :param box_coords: The rectangular patch coordi

Get all the record token that intersects or within a particular rectangular patch. :param box_coords: The rectangular patch coordinat

Get the reference points used in SCA and TSA. Args: H, W: spatial shape of bev. Z: hight of pillar. D: sam

Get the reference points used in SCA and TSA. Args: H, W: spatial shape of bev. Z: hight of pillar. D: sam

Get relative positional embeddings according to the relative positions of query and key sizes. Args: q_size (int): size of qu

Get precessed :obj:`InstanceData` of multiple images.