Initialize classification branch and regression branch of head.

Initialize classification branch and regression branch of head.

Test function with augmentaiton.

Test function with augmentaiton.

Convert action for single file. Args: file_idx (int): Index of the file to be converted.

convert kitti info v1 to v2 if possible. Args: info (dict): Info of the input kitti data. - image (dict): image info

Create indoor information file. Get information of the raw data and save it to the pkl file. Args: data_path (str): Path of the data

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

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

Create reduced point clouds for training/validation/testing. Args: data_path (str): Path of original data. pkl_prefix (str): Pref

Create info file of waymo dataset. Given the raw data, generate its related info file in pkl format. Args: data_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

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

Extract features of points.

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

Forward function. Args: mlvl_feats (tuple[Tensor]): Features from the upstream network, each is a 4D-tensor with s

Forward function for `Detr3DTransformer`. Args: mlvl_feats (list(Tensor)): Input queries from different level. Eac

Forward function for `Detr3DTransformerDecoder`. Args: query (Tensor): Input query with shape `(num_query, bs, emb

Forward Function of Detr3DCrossAtten. Args: query (Tensor): Query of Transformer with shape (num_query, bs, embed_

Forward function for `DGCNN`. **kwargs allow passing a more general data flow when combining with other operations in `DGCNN`.

Forward function for `TransformerDecoder`. Args: query (Tensor): Input query with shape `(num_query, bs, embed_dim

Calls either forward_train or forward_test depending on whether return_loss=True. Note this setting will change the expected inputs. W

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

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

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

Initialize weights of the head.

Initialize the transformer weights.

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

Test function of point cloud branch.

Convert the model into training mode while keep normalization layer freezed.