multi-scale deformable attention for 3D space Args: value (torch.Tensor): The value has shape (bs, num_keys, mum_heads, e

Convert boxes from :obj:`NuScenesBox` to :obj:`CameraInstance3DBoxes`. Args: boxes (list[:obj:`NuScenesBox`]): List of predicted NuScene

Obtain history BEV features iteratively. To save GPU memory, gradients are not calculated. Args: prev_img_f

Obtain history BEV features iteratively. To save GPU memory, gradients are not calculated. Args: prev_img_f

Parse config from strings. Args: config_strings (string): strings of model config. Returns: Config: model config

Parse one prediction with several instances in kitti format and convert them to `Object` proto. Args: kitti_result (dict):

Produces a colored string for printing Parameters ---------- string : str String that will be colored color : str

This method performs point sampling by converting reference points from a 3D coordinate system to a 2D BEV (Bird's Eye View) coordinate syst

This method performs point sampling by converting reference points from a 3D coordinate system to a 2D BEV (Bird's Eye View) coordinate syst

Get the intersection of the convex hull of the reprojected bbox corners and the image canvas, return None if no intersection. Args: c

Get the intersection of the convex hull of the reprojected bbox corners and the image canvas, return None if no intersection. Args: c

Prepare data for testing. Args: index (int): Index for accessing the target data. Returns: dict: Tes

prepare data for training Args: index (Int): the index of the data Returns: data (Dict): the data dic

Training data preparation. Args: index (int): Index for accessing the target data. Returns: dict: Tra

print the final IoU results. Called by function `print`. Use mIoU_type_str to control the output. Args: hist (np.arra

Process stereo features before fusion. Args: stereo_feats (torch.Tensor): Stereo features. shape (B, N, C, H, W)

Random sampling. Sampling point cloud to a certain number of points. Args: points (ndarray): Point cloud. num_points (int):

Render sample data onto axis. :param sample_data_token: Sample_data token. :param with_anns: Whether to draw box annotations. :pa

Prepare the info file for s3dis dataset. Args: root_path (str): Path of dataset root. info_prefix (str): The prefix of info filen

Parse and save the calibration data. Args: frame (:obj:`Frame`): Open dataset frame proto. file_idx (int): Current fi

Parse and save the label data in txt format. The relation between waymo and kitti coordinates is noteworthy: 1. x, y, z correspond to

Parse and save the lidar data in psd format. Args: frame (:obj:`Frame`): Open dataset frame proto. file_idx (int): Cu

Parse and save the pose data. Note that SDC's own pose is not included in the regular training of KITTI dataset. KITTI raw dataset co

Prepare the info file for scannet dataset. Args: root_path (str): Path of dataset root. info_prefix (str): The prefix of info fil

Visualize 3D point cloud and 3D bboxes.

Visualize 3D bboxes on 2D image by projection.

Visualize 3D point cloud and segmentation mask.

Test function without augmentaiton. Args: img (torch.Tensor): Images of each sample with shape (bs, n_views, C, H, W).

Test Function without augmentaiton. Args: img (torch.Tensor): multi view image input of current frame. shape (B, N, C, H,

Test function without augmentaiton. Args: img_metas (list[dict]): Meta information of each sample. img (t

Test function without augmentaiton.

Prepare the info file for sunrgbd dataset. Args: root_path (str): Path of dataset root. info_prefix (str): The prefix of info fil

Make sure different ranks share the same seed. All workers must call this function, otherwise it will deadlock. This method is generally used

Do Temporal Fusion. Args: Returns: fusion_results (dict): with keys "_bev_embed, extra". _bev_embed (

Do Temporal Fusion. Args: Returns: fusion_results (dict): with keys "bev_embed, extra". bev_embe

Convert points and bboxes to Depth Coord and Depth Box mode.

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

convert sample queue into one single sample. Args: queue (List[Dict]): the sample queue Returns: que

convert sample queue into one single sample. Args: queue (List[Dict]): the sample queue Returns: que

Prepare the info file for waymo dataset. Args: root_path (str): Path of dataset root. info_prefix (str): The prefix of info filen

Args: bbox_pred (Tensor): Predicted boxes with normalized coordinates (cx, cy, w, h), which are all in range [0,

Call function to pad images, masks, semantic segmentation maps. Args: results (dict): Result dict from loading pipeline. R

Call function to normalize images. Args: results (dict): Result dict from loading pipeline. Returns:

Call function to perform photometric distortion on images. Args: results (dict): Result dict from loading pipeline. Return

Call function to pad images, masks, semantic segmentation maps. Args: results (dict): Result dict from loading pipeline.

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

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

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

Get item from infos according to the given index. Returns: dict: Data dictionary of the corresponding index.