Apply hard voxelization to points.

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

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Heigh

Call function to sample ground truth objects to the data. Args: data (dict): Result dict from loading pipeline. Returns:

Private function to rotate, scale and translate bounding boxes and points. Args: input_dict (dict): Result dict from load

Call function to flip points, values in the ``bbox3d_fields`` and also flip 2D image and its annotations. Args: input_dic

Call function to load multi-view image from files. Args: results (dict): Result dict containing multi-view image filenames.

Call function to transform and format common fields in results. Args: results (dict): Result dict contains the data to convert.

Call function to collect keys in results. The keys in ``meta_keys`` will be converted to :obj:`mmcv.DataContainer`. Args:

str: Return a string that describes the module.

str: Return a string that describes the module.

Evaluation for a single model in Lyft protocol. Args: result_path (str): Path of the result file. logger (logging.Log

Function: pillar pooling (backward, cuda) Args: out_grad : input features, FloatTensor[b, d, h, w, c] geom_feats : input coord

Function: pillar pooling (forward, cuda) Args: x : input features, FloatTensor[n, c] geom_feats : input coordinates, In

Create info file of lyft dataset. Given the raw data, generate its related info file in pkl format. Args: root_path (str): Path of t

Create info file of nuscene dataset. Given the raw data, generate its related info file in pkl format. Args: root_path (str): Path o

Export 2d annotation from the info file and raw data. Args: root_path (str): Root path of the raw data. info_path (str): Path of

Export 2d annotation from the info file and raw data. Args: root_path (str): Root path of the raw data. info_path (str): Path of

Filter ground truths by difficulties. Args: db_infos (dict): Info of groundtruth database. removed_difficulty (list):

Filter ground truths by number of points in the bbox. Args: db_infos (dict): Info of groundtruth database. min_gt_poi

x: x.shape -> [B, H*W, C] hw_shape: (H, W)

Args: x (tensor): input features with shape of (num_windows*B, N, C) mask (tensor | None, Optional): mask with shape

Forward pass. Args: feats (list[torch.Tensor]): Multi-level features, e.g., features produced by FPN. Retu