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

Since teacher_model is registered as a plain object, it is necessary to put the teacher model to cuda when calling cuda function.

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

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

Apply function to a list of arguments. Note: This function applies the ``func`` to multiple inputs and map the multiple outputs o

Build loss.

Change the device of the data inplace. Example: >>> self = SamplingResult.random() >>> print(f'self = {self.to(None)}

str: The device of the points are on.

Convert a list of bboxes to roi format. Args: bbox_list (list[Tensor]): a list of bboxes corresponding to a batch of images.

See :func:`BaseInstanceMasks.expand`.

Convert targets by image to targets by feature level. [target_img0, target_img1] -> [target_level0, target_level1, ...]

See :func:`BaseInstanceMasks.to_ndarray`.

Assign gt to bboxes. The assignment is done in following steps 1. compute iou between all bbox (bbox of all pyramid levels) and gt

Decode the predicted bboxes according to prediction and base boxes.

Concatenate a list of Boxes into a single Boxes. Args: boxes_list (list[:obj:`BaseInstances3DBoxes`]): List of boxes. Re

Build loss function.

Convert action.

Unmap a subset of item (data) back to the original set of items (of size count)

Compute losses of the head. Args: cls_scores (list[Tensor]): Cls and quality scores for each scale level has shap

dict: a dictionary of info about the object

Call all hooks. Args: fn_name (str): The function name in each hook to be called, such as "before_train_epoch".

Register a hook into the hook list. The hook will be inserted into a priority queue, with the specified priority (See :class:`Priorit

Sample positive and negative bboxes. This is a simple implementation of bbox sampling given candidates, assigning results and ground

Convert the model into training mode will keeping the normalization layer freezed.

Args: size (tuple): expected shape of dummy masks, (H, W) or (N, H, W) Return: ndarray: dummy mask

Build head.

Decode predicted parts to bbox3d. Args: bbox_out (dict): Predictions from model, should contain keys below. - ce

Builder of box assigner.

Build detector.

Args: size (tuple): expected shape of dummy masks, (N, H, W) Return: list[list[ndarray]]: dummy mask

Initialize the weights of FPN module.

Calculate the ious between each bbox of bboxes1 and bboxes2. Args: bboxes1(ndarray): shape (n, 4) bboxes2(ndarray): shape (k, 4)

Builder of box sampler.

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

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

Build head.

Convert points from `src` mode to `dst` mode. Args: point (tuple | list | np.dnarray | torch.Tensor | BasePoints)

Generate bboxes from vote head predictions. Args: points (torch.Tensor): Input points. bbox_preds (dict): Predictions

NMS for multi-class bboxes. Args: multi_bboxes (Tensor): shape (n, #class*4) or (n, 4) multi_scores (Tensor): shape (n, #class),

Generate random bitmap masks for demo / testing purposes. Example: >>> from mmdet.core.mask.structures import BitmapMasks

Convert detection results to a list of numpy arrays. Args: bboxes (torch.Tensor | np.ndarray): shape (n, 5) labels (torch.Tensor

Decode distance prediction to bounding box. Args: points (Tensor): Shape (B, N, 2) or (N, 2). distance (Tensor): Distance from th

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

Compute loss. Args: bbox_preds (dict): Predictions from forward of vote head. points (list[torch.Tensor]): Input poin

mPtr[((i1 * mShape[1] + i2) * mShape[2] + i3) * mShape[3] + i4];

Build a module. Args: cfg (dict, list[dict]): The config of modules, is is either a dict or a list of configs. regist

Builder of box coder.

Flip the points in BEV along given BEV direction.

See :func:`BaseInstanceMasks.flip`.

Loss function of DIIHead, get loss of all images. Args: cls_score (Tensor): Classification prediction results of

Make sparse convolution module. Args: in_channels (int): the number of input channels out_channels (int): the number of out chann

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

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

Get root logger. Args: log_file (str, optional): File path of log. Defaults to None. log_level (int, optional): The level of logg

Parse the raw outputs (losses) of the network. Args: losses (dict): Raw output of the network, which usually contain

Build detector.

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

torch.Shape: Shape of points.

Create a superset of inputs needed to run test or train batches. Args: input_shape (tuple): input batch dimensions n

Calculate accuracy according to the prediction and target. Args: pred (torch.Tensor): The model prediction, shape (N, num_class)

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

Extract features. Args: img (torch.Tensor): Image tensor with shape (n, c, h ,w). Returns: list[torch.Tensor

Get anchors according to feature map sizes. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes. img_met

Get targets for PAA head. This method is almost the same as `AnchorHead.get_targets()`. We direct return the results from _get_target

Calculate the ground truth for all samples in a batch according to the sampling_results. Almost the same as the implementation in bbo

Convert objects of various python types to :obj:`torch.Tensor`. Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`, :class:`S

Encode deltas between bboxes and ground truth boxes.

forward. Args: k (int): number of nearest neighbors. xyz (Tensor): (B, N, 3) if transposed == False, else (B, 3, N).

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

Obtain the mean of tensor on different GPUs.

Scale the points with horizontal and vertical scaling factors. Args: scale_factors (float): Scale factors to scale the points.

Convert boxes from `src` mode to `dst` mode. Args: box (tuple | list | np.dnarray | torch.Tensor | BaseInstance3D

Get segmentation masks from mask_pred and bboxes. Args: mask_pred (Tensor or ndarray): shape (n, #class, h, w). F

Check if is ResNet building block.

Validate the output of the onnxruntime backend is the same as the output generated by torch. Args: model (nn.Module): the model to be

Random select some elements from the gallery. If `gallery` is a Tensor, the returned indices will be a Tensor; If `gallery` is a ndar