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

Run the model in onnxruntime env. Args: feat (list[Tensor]): A list of tensors from torch.rand, each is a 4D-tensor. Ret

str: a "nice" summary string describing this module

Compute assignment by checking whether point is inside bbox. Args: bboxes_3d (BaseInstance3DBoxes): Instance of bounding boxes.

Forward function of roi_extractor and bbox_head used in both training and testing. Args: seg_feats (torch.Tensor): Point-

Box head forward function used in both training and testing.

Check whether the `num_classes` in head matches the length of `CLASSSES` in `dataset`. Args: runner (obj:`EpochBasedRunne

Crop image with a given center and size, then paste the cropped image to a blank image with two centers align. This function is equiv

Evaluation for a single model in nuScenes protocol. Args: result_path (str): Path of the result file. logger (logging

Evaluation for a single model in Lyft protocol. Args: result_path (str): Path of the result file. logger (logging.Log

Check whether the center of each box is in the patch. Args: patch (list[int]): The cropped area, [left, top, right, bottom].

Convert the results to the standard format. Args: results (list[dict]): Testing results of the dataset. jsonfile_pref

Convert the results to the standard format. Args: results (list[dict]): Testing results of the dataset. jsonfile_pref

Fuse global context feats with roi feats.

Transform outputs for a batch item into bbox predictions. Args: cls_score_list (list[Tensor]): Box scores for a single scale leve

Transform outputs for a single batch item into bbox predictions. Args: cls_scores (list[Tensor]): Box iou-aware scores for a sing

Get final border for the target size. This function generates a ``final_border`` according to image's shape. The area between ``final

Find the predefined detector config directory.

Find the predefined detector config directory.

Load a configuration as a python module.

Load a configuration as a python module.

Load a configuration as a python module.

Grab configs necessary to create a detector. These are deep copied to allow for safe modification of parameters without influencing other tes

Sample fine grained feats from each level feature map and concatenate them together.

Grab configs necessary to create a bbox_head. These are deep copied to allow for safe modification of parameters without influencing other te

Compute the equation of the plane. Args: vector1 (torch.Tensor): Parallel vector of the plane. vector2 (torch.Tensor)

Grab configs necessary to create a roi_head. These are deep copied to allow for safe modification of parameters without influencing other tes

Estimate uncertainty based on pred logits. We estimate uncertainty as L1 distance between 0.0 and the logits prediction in 'mask_pred

Grab configs necessary to create a vote_head. These are deep copied to allow for safe modification of parameters without influencing other te

Initialize rule, key_indicator, comparison_func, and best score. Args: rule (str | None): Comparison rule for best score.

Override the method in the parent class to avoid changing para's name.

Private function to load point clouds data. Args: pts_filename (str): Filename of point clouds data. Returns:

Extract local maximum pixel with given kernel. Args: heat (Tensor): Target heatmap. kernel (int): Kernel size of max

Mask refining process with point head in testing.

Generate mesh grid of x and y. Args: x (torch.Tensor): Grids of x dimension. y (torch.Tensor): Grids of y dimension.

Randomly get another item with the same flag. Returns: int: Another index of item with the same flag.

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

Removes point too close within a certain radius from origin. Args: points (np.ndarray): Sweep points. radius (float):

Removes point too close within a certain radius from origin. Args: points (np.ndarray | :obj:`BasePoints`): Sweep points.

Resize bounding boxes with ``results['scale_factor']``.

Resize masks with ``results['scale']``

Resize semantic segmentation map with ``results['scale']``.

Rotate 2D boxes. Args: corners (np.ndarray): Corners of boxes. angle (float): Rotation angle. rot_mat_T (np.ndarray): Tra

Sample points for each points subset. Args: points (np.ndarray): Points subset to be sampled. sampler (VoxelGenerator

Select transform. Args: transform (np.ndarray): Transforms to select from. indices (np.ndarray): Mask to indicate which transform

Split coordinates and features of input points. Args: points (torch.Tensor): Point coordinates with features, wit

Get top k positions from heatmap. Args: scores (Tensor): Target heatmap with shape [batch, num_classes, height, w

Export oriented (around Z axis) scene bbox to meshes. Args: scene_bbox(list[ndarray] or ndarray): xyz pos of center and 3 len

Add segmentation mask to visualizer via per-point colorization. Args: seg_mask_colors (numpy.array, shape=[N, 6]):

Import a module from albumentations. It inherits some of :func:`build_from_cfg` logic. Args: cfg (dict): Config dict. It

Allreduce gradients. Args: params (list[torch.Parameters]): List of parameters of a model coalesce (bool, optional): Whether allr

Get offest for deformable conv based on anchor shape NOTE: currently support deformable kernel_size=3 and dilation=1 Args:

Compute regression and classification targets for anchors. Args: anchor_list (list[list]): Multi level anchors of each image.

Convert continuous angle to a discrete class and a residual. Convert continuous angle to a discrete class and a small regression numb

Test function with augmentaiton.

Attach a text label above each bar in *rects*, displaying its height.

Calculate average precision (for single or multiple scales). Args: recalls (np.ndarray): Recalls with shape of (num_scales, num_dets) \

Convert results to kitti format for evaluation and test submission. Args: net_outputs (List[np.ndarray]): list of array storing t

Map bboxes from testing scale to original image scale. Args: bboxes (:obj:`BaseInstance3DBoxes`): Boxes to be mapped back. scale_

Flip bboxes horizontally or vertically. Args: bboxes (Tensor): Shape (..., 4*k) img_shape (tuple): Image shape. direction

Split batch bbox prediction back to each image.

Rescale bounding box w.r.t. scale_factor. Args: bboxes (Tensor): Shape (n, 4) for bboxes or (n, 5) for rois scale_factor (float):

Check whether the training dataset is compatible with head. Args: runner (obj:`EpochBasedRunner`): Epoch based Runner.

Check whether the dataset in val epoch is compatible with head. Args: runner (obj:`EpochBasedRunner`): Epoch based Runner.