Create reduced point clouds for given info. Args: data_path (str): Path of original data. info_path (str): Path of data info.

Decode bboxes. Args: all_cls_scores (Tensor): Outputs from the classification head, \ shape [nb_dec, bs, num_query

Inverse function of sigmoid. Args: x (Tensor): The tensor to do the inverse. eps (float): EPS avoid numerical

Args: input_ch(int) : the number of input channel out_features (list[str]): name of the layers whose outputs should

Generate bboxes from bbox head predictions. Args: preds_dicts (tuple[list[dict]]): Prediction results. img_metas (list

Obtain the info with RT matric from general sensor to Top LiDAR. Args: nusc (class): Dataset class in the nuScenes dataset. senso

Given the raw data, generate the ground truth database. Args: dataset_class_name （str): Name of the input dataset. data_path (str

Get data infos. This method gets information from the raw data. Args: num_workers (int): Number of threads to be used. D

KITTI annotation format version 2: { [optional]points: [N, 3+] point cloud [optional, for kitti]image: { image_id

Waymo annotation format version like KITTI: { [optional]points: [N, 3+] point cloud [optional, for kitti]image: {

Computes one-to-one matching based on the weighted costs. This method assign each query prediction to a ground truth or background. Th

1x1 convolution with padding

3x3 convolution with padding

Convert action.

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

Extract features from images and points.

During inference, the functionary of batch norm layers is turned off but only the mean and var alone channels are used, which exposes the chance t

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

Get available scenes from the input nuscenes class. Given the raw data, get the information of available scenes for further info generation.

Default initialization for Parameters of Module.

Inverse function of sigmoid. Args: x (Tensor): The tensor to do the inverse. eps (float): EPS avoid numerical

Loss function. Args: gt_bboxes_list (list[Tensor]): Ground truth bboxes for each image with shape (nu

Prepare data related to Lyft dataset. Related data consists of '.pkl' files recording basic infos. Although the ground truth database and 2D

Prepare data related to nuScenes dataset. Related data consists of '.pkl' files recording basic infos, 2D annotations and groundtruth databas

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

Convert class_id in loaded segmentation mask to label.

Convert class_id in loaded segmentation mask to label.

Generate the train/val infos from the raw data. Args: nusc (:obj:`NuScenes`): Dataset class in the nuScenes dataset. train_scenes

Generate the train/val infos from the raw data. Args: lyft (:obj:`LyftDataset`): Dataset class in the Lyft dataset. train_scenes

Pad images according to ``self.size``.

Test function of point cloud branch with augmentaiton. The function implementation process is as follows: - step 1: map features b

Build data config for loading visualization data.

Convert transformation matrix in Cartesian coordinates to homogeneous format. Args: mat (np.ndarray): Transformation matr

Convert keys in pycls pretrained RegNet models to mmdet style.

Create folder for data preprocessing.

Decode bboxes. Args: cls_scores (Tensor): Outputs from the classification head, \ shape [num_query, cls_out_channe

3x3 convolution with padding

Extract features of images.

Forward function for point cloud branch. Args: pts_feats (list[torch.Tensor]): Features of point cloud branch gt_bboxe

Forward training function. Args: points (list[torch.Tensor], optional): Points of each sample. Defaults to None.

Generate one 2D annotation record given various informations on top of the 2D bounding box coordinates. Args: ann_rec (dict): Origina

Generate one 2D annotation record given various informations on top of the 2D bounding box coordinates. Args: ann_rec (dict): Origina

Get the 2D annotation records for a given `sample_data_token`. Args: sample_data_token (str): Sample data token belonging to a camera \

Convert instance masks to axis-aligned bounding boxes. Args: points (np.array): Scene points of shape (n, 6). pts_ins

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

Get semantic segmentation map for an image. Args: nuim (obj:`NuImages`): NuImages dataset object img_info (dict): Meta informatio

Get data infos. This method gets information from the raw data. Args: num_workers (int): Number of threads to be used. D

Compute scene_idxs for data sampling and label weight for loss \ calculation. We sample more times for scenes with more points. Label

Compute scene_idxs for data sampling and label weight for loss \ calculation. We sample more times for scenes with more points. Label

Compute regression and classification targets for a batch image. Outputs from a single decoder layer of a single feature level are used.

Compute regression and classification targets for a batch image. Outputs from a single decoder layer of a single feature level are used.

Initialize layers of the Detr3DTransformer.