Concatenate a list of Points into a single Points. Args: points_list (list[:obj:`BasePoints`]): List of points. Returns:

Returns a record from the layer in constant runtime. :param layer_name: Name of the layer that we are interested in. :param t

Convert current points to a specific device. Args: device (str | :obj:`torch.device`): The name of the device. Returns:

Load a config file. Args: filename: absolute path or relative path w.r.t. the current working directory keys

Clone the Points. Returns: :obj:`BasePoints`: Box object with the same properties as self.

Create a copy of self. :return: A copy.

Concatenates a list of Boxes into a single Boxes Arguments: boxes_list (list[Boxes]) Returns: Boxes

Returns: str: a yaml string representation of the config

Build loss function.

Returns the field called `name`.

Returns all EvalBoxes in a list.

Rotate points with the given rotation matrix or angle. Args: rotation (float | np.ndarray | torch.Tensor): Rotation matrix

Normalize the feature maps to have zero mean and unit variances. Args: feat (torch.Tensor): The original feature map with shape

Clip (in place) the boxes by limiting x coordinates to the range [0, width] and y coordinates to the range [0, height]. Args

Decode regression into locations, dimensions, orientations. Args: reg (Tensor): Batch regression for each predict center2d point.

Concatenate a list of Boxes into a single Boxes. Args: boxes_list (list[:obj:`BaseInstance3DBoxes`]): List of boxes. Ret

Translate points with the given translation vector. Args: trans_vector (np.ndarray, torch.Tensor): Translation ve

Args: norm (str or callable): either one of BN, SyncBN, FrozenBN, GN; or a callable that takes a channel number and returns

Convert detection results to a list of numpy arrays. Args: bboxes (torch.Tensor): Bounding boxes with shape (N, 5). labels (torch

Save a config object to a yaml file. Note that when the config dictionary contains complex objects (e.g. lambda), it can't be

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

Loss function. Args: gt_bboxes_list (list[Tensor]): Ground truth bboxes for each image with shape (num_gts, 4) in

Extract features from points.

Flip the points along given BEV direction. Args: bev_direction (str): Flip direction (horizontal or vertical).

Clone the Boxes. Returns: :obj:`BaseInstance3DBoxes`: Box object with the same properties as self.

A function warpper for building 3D detector or segmentor according to cfg. Should be deprecated in the future.

Efficient version of torch.cat that avoids a copy if there is only a single element in a list

Load checkpoint from a file or URI. Args: model (Module): Module to load checkpoint. filename (str): Accept local filepath, URL, `

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataloade

Build head.

Args: predictions: D2 Instances for predictions of the current frame Return: D2 Instances for predictions of

Encode CameraInstance3DBoxes by locations, dimensions, orientations. Args: locations (Tensor): Center location for 3D boxes.

This function would modify some filed to keep the compatibility of config. For example, it will move some args which will be deprecated to th

Convert bbox coordinates from (cx, cy, w, h) to (x1, y1, x2, y2). Args: bbox (Tensor): Shape (n, 4) for bboxes. Returns: Ten

Convert self to ``dst`` mode. Args: dst (:obj:`CoordMode`): The target Box mode. rt_mat (np.ndarray | torch.Tensor, o

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

nn.Module: normalization layer after the first convolution layer

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

Convert current boxes to a specific device. Args: device (str | :obj:`torch.device`): The name of the device. Returns:

nn.Module: normalization layer after the second convolution layer

This function is a replacement of .to(another_device) such that it allows the casting to be traced properly by explicitly calling the underly

Limit the value into a period for periodic function. Args: val (torch.Tensor | np.ndarray): The value to be converted. offset (fl

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

Project points in camera coordinates to image coordinates. Args: points_3d (torch.Tensor | np.ndarray): Points in shape (N, 3) pr

Rotate points by angles according to axis. Args: points (np.ndarray | torch.Tensor | list | tuple ): Points of shape (N, M, 3

Returns a list of records corresponding to the layer name. :param layer_name: Name of the layer that will be loaded. :return:

Build backbone.

Clone the Boxes. Returns: Boxes

Convert input array to target data type. Args: input_array (tuple | list | np.ndarray | torch.Tensor | int | floa

Normalize the feature maps to have zero mean and unit variances. Args: feat (torch.Tensor): The original feature map with shape

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

Remove the field called `name`.

Inverse function of sigmoid. Args: x (Tensor): The tensor to do the inverse. eps (float): EPS avoid numerical

nn.Module: normalization layer after the third convolution layer

Convert a rotated boxes in XYWHR format to XYXYR format. Args: boxes_xywhr (torch.Tensor | np.ndarray): Rotated boxes in XYWHR format.

Build neck.

r"""Checkpoint a model or part of the model Checkpointing works by trading compute for memory. Rather than storing all intermediate activatio

Helper for building a conv2d layer.

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

Create a new box object with data. The new box and its tensor has the similar properties as self and self.tensor, respectively.

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

Convert points from `src` mode to `dst` mode. Args: point (tuple | list | np.ndarray | torch.Tensor | :obj:`BaseP