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

Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without affecting the

Dump the detection results to a COCO style json file. There are 3 types of results: proposals, bbox predictions, mask predictions, and

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

Save the timestamp data in a separate file instead of the pointcloud. Note that SDC's own pose is not included in the regular trainin

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 point cloud and 3D bboxes.

Visualize 3D bboxes on 2D image by projection.

Visualize 3D bboxes on 2D image by projection.

Visualize 3D point cloud and segmentation mask.

Visualize 3D point cloud and segmentation mask.

Test function without augmentaiton.

Test function without augmentaiton.

Test det bboxes without test-time augmentation. Args: feats (tuple[torch.Tensor]): Multi-level features from the

Test function

Test function

Generate the valid flags of points of a single feature map. Args: featmap_size (tuple[int]): The size of feature maps, arrange as

Inference by sliding-window with overlap. If h_crop > h_img or w_crop > w_img, the small patch will be used to decode without padding

Inference by sliding-window with overlap. If h_crop > h_img or w_crop > w_img, the small patch will be used to decode without padding

Smooth L1 loss. Args: pred (torch.Tensor): The prediction. target (torch.Tensor): The learning target of the prediction. b

Save the current parameters for restoring later. Args: model: A model that parameters will be stored

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

Deserialize tensor to picklable python object.

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

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

Masks logits such that logits not in top-k are small.

Masks logits using nucleus (top-p) sampling.

Return the conversion function from torch to the intermediate representation. Args: ir_type (IR): The type of the intermediate repres

Return the conversion function from torch to the intermediate representation. Args: ir_type (IR): The type of the intermediate repres

The iteration step during training. This method defines an iteration step during training, except for the back propagation and optimi

The iteration step during validation. This method shares the same signature as :func:`train_step`, but used during val epochs. Note t

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

Inference with full image.

Inference with full image.

Call function to resize images, bounding boxes, masks, semantic segmentation map. Args: results (dict): Result dict from

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

Call function to process the image with gamma correction. Args: results (dict): Result dict from loading pipeline. Retur

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

Args: cls_pred (Tensor): Predicted classification logits, shape [num_query, num_class]. gt_labels (Te

Args: cls_pred (Tensor): Predicted classfication logits in shape (N1, H, W), dtype=torch.float32. gt_