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

Args:

Returns: pred_dist: Categorical predictive distribution with batch shape [batch_size, seq_length].

we use teacher force strategy

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

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

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

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

Generate the attention mask for causal decoding

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

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

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

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

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

Convert vertices from its original range ([-1,1]) to discrete values in [0, n_bits**2 - 1]. Args: polyline (array): point coordinates, sh

Transform network outputs for a batch into bbox predictions. Args: all_cls_scores_list (list[Tensor]): Classification outputs

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

obtain bev features.

Find the each refence point's corresponding pixel in each camera Args: reference_points: [B, num_query, 3] eg

Find the each refence point's corresponding pixel in each camera Args: reference_points: [B, num_query, 3] eg

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

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

get dynamic line with difference approach mat: N1xN2xnpts m1: N1xnpts m2: N2xnpts

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, optional): Number of threads to

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

Args: group_queries (int): Number of dn queries in one group.

Generate bboxes from bbox head predictions. Args: predss : occ results. img_metas (list[dict]): Point cloud and image'

Returns the data path as well as all annotations related to that sample_data. Note that the boxes are transformed into the current sensor's c

Get the position embedding of proposal.

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

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

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

Compute classification and mask targets for all images for a decoder layer. Args: cls_scores_list (list[Tensor]): Mask sc

Compute classification and mask targets for all images for a decoder layer. Args: cls_scores_list (list[Tensor]): Mask sc

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

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

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

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.