Build neck.

See :func:`BaseInstanceMasks.crop`.

Evaluate mAP of a dataset. Args: det_results (list[list]): [[cls1_det, cls2_det, ...], ...]. The outer list indicates images,

Evaluation in Lyft protocol. Args: results (list[dict]): Testing results of the dataset. metric (str | list[str]): Me

Args: feat: shape=[N, C], N is the voxel num in the batch. voxel_drop_lvl: shape=[N, ]. Indicates drop_level of the window the vo

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

Get category ids of concatenated dataset by index. Args: idx (int): Index of data. Returns: list[int]: All c

Generate grid anchors in multiple feature levels. Args: featmap_sizes (list[tuple]): List of feature map sizes in

Limit the value into a period for periodic function. Args: val (np.ndarray): The value to be converted. offset (float, optional):

Limit the value into a period for periodic function. Args: val (torch.Tensor): The value to be converted. offset (float, optional

In distributed setting, this function only download checkpoint at local rank 0.

Merge augmented detection bboxes and scores. Args: aug_bboxes (list[Tensor]): shape (n, 4*#class) aug_scores (list[Tensor] or Non

Test model with multiple gpus. This method tests model with multiple gpus and collects the results under two different modes: gpu and cpu mod

nn.Module: the normalization layer named "norm2"

Initialization before data preparation. Args: results (dict): Dict before data preprocessing. - img_fields (list

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

Set random seed. Args: seed (int): Seed to be used. deterministic (bool): Whether to set the deterministic option for

Apply dynamic voxelization to points. Args: points (list[torch.Tensor]): Points of each sample. Returns: tup

Set attribute, i.e. self.name = value This reloading prevent the teacher model from being registered as a nn.Module. The teacher modu

Generate targets of line primitive. Args: point_mask (torch.Tensor): Tensor to store the ground truth of mask.

Box head forward function used in both training and testing.

Box head forward function used in both training and testing.

Draw points on visualizer. Args: points (numpy.array | torch.tensor, shape=[N, 3+C]): points to visualize. vis (:obj:`

Given feats and indexes, returns the gathered feats. Args: feats (torch.Tensor): Features to be transposed and gathered

Mask head forward function used in both training and testing.

Randomly sample an img_scale according to ``ratio_range`` and ``multiscale_mode``. If ``ratio_range`` is specified, a ratio will be s

Save the current checkpoint and delete unwanted checkpoint.

Write points into ``obj`` format for meshlab visualization. Args: points (np.ndarray): Points in shape (N, dim). out_filename (str

Get the flag indicate whether anchor centers are inside regions.

Convert 3D detection results to kitti format for evaluation and test submission. Args: net_outputs (list[np.ndarray]): Li

Map bboxes from testing scale to original image scale.

Build backbone.

Calculate region of the box defined by the ratio, the ratio is from the center of the box to every edge.

Calculate a proportional bbox region. The bbox center are fixed and the new h' and w' is h * ratio and w * ratio. Args: bbox (Tensor

Convert points in camera coordinate to lidar coordinate. Args: points (np.ndarray, shape=[N, 3]): Points in camera coordinate. r_

Coerces input into a random number generator. If the input is None, then a global random state is returned. If the input is a numeric value,

Kitti eval. support 2d/bev/3d/aos eval. support 0.5:0.05:0.95 coco AP. Args: gt_annos (dict): Must from get_label_annos() in kitti_common

Directly extract features from the backbone+neck.

Extract features from multiple images. Args: imgs (list[torch.Tensor]): A list of images. The images are augmente

see :func:`BaseInstanceMasks.flip`

Args: input: NC 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 class names of a dataset.

Args: win_inds indicates which windows a voxel belongs to. Voxels share a window have same inds. shape = [N,] Return:

Compute surface and line center of bounding boxes. Returns: torch.Tensor: Surface and line center of bounding boxes.

Check if is one of the norms.

Concat multi-level feature maps by image. [feature_level0, feature_level1...] -> [feature_image0, feature_image1...] Convert the shape of eac

Make plugins for ResNet ``stage_idx`` th stage. Currently we support to insert ``context_block``, ``empirical_attention_block``, ``no

Match points to corresponding line. Args: points (torch.Tensor): Points of input. corners (torch.Tensor): Eight corne

Merge augmented detection 3D bboxes and scores. Args: aug_results (list[dict]): The dict of detection results. The dict conta

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

See :func:`BaseInstanceMasks.pad`.

Converting the points set into bounding box. :param pts: the input points sets (fields), each points set (fields) is represented

Prepare an example input image for ``generate_inputs_and_wrap_model``. Args: input_config (dict): customized config describing the exampl

See :func:`BaseInstanceMasks.rescale`.

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

Sample specific number of ground truths. Args: num (int): Sampled number. Returns: list[dict]: Sampled groun

Convert multi-modality detection results into 2D results. Project the predicted 3D bbox to 2D image plane and visualize them. Args: im

Split side-aware features aligned with orders of bucketing targets.

Split predicted features to specific parts. Args: cls_preds (torch.Tensor): Class predicted features to split. reg_pr

See :func:`BaseInstanceMasks.to_tensor`.

Convert ``xyxy`` style bounding boxes to ``xywh`` style for COCO evaluation. Args: bbox (numpy.ndarray): The bounding box

Add shared or separable branch.