Calculate 3D IoU using cuda implementation. Note: This function calculate the IoU of 3D boxes based on their volumes.

Calculate IoU between 2D bboxes. Args: bboxes1 (Tensor): shape (B, m, 6) in <x1, y1, z1, x2, y2, z2> format or em

Compute match cost. Args: pred_instances (:obj:`InstanceData`): Instances of model predictions. It includes ``pri

Compute match cost. Args: bbox_pred (Tensor): Predicted boxes with normalized coordinates (cx,cy,l,w,cz,h,sin(φ),

Compute match cost. Args: pred_logits (Tensor): Shape [num_query, C]. gt_logits (Tensor): Shape [num_gt, C].

Compute match cost. Args: pred_instances (:obj:`InstanceData`): Predicted instances which must contain ``scores``

Compute match cost. Args: pred_instances (:obj:`InstanceData`): Predicted instances which must contain ``scores``

Args: item (int or slice or np.ndarray or Tensor): Index of boxes. Note: The following usage are allowed:

Args: item (str, int, list, :obj:`slice`, :obj:`numpy.ndarray`, :obj:`torch.LongTensor`, :obj:`torch.BoolTensor`)

Args: item (int or tuple or slice or np.ndarray or Tensor): Index of points. Note: The follo

Args: item (int or slice or np.ndarray or Tensor): Index of boxes. Note: The following usage are allowed:

Creates a line represented as sequence of cylinder triangular meshes. Arguments: points {ndarray} -- Numpy array of ponts

Creates a line represented as sequence of cylinder triangular meshes. Arguments: points {ndarray} -- Numpy array of ponts

Yield a point as a Tensor at a time. Returns: Iterator[Tensor]: A point of shape (points_dim, ).

Yield a box as a Tensor at a time. Returns: Iterator[Tensor]: A box of shape (box_dim, ).

int: Number of boxes in the current object.

int: The length of `PointData`.

int: Number of boxes in the current object.

str: Return a string that describes the module.

str: return a string that describes the module

str: a string describing the module

str: Return a string that describes the object.

str: Return a string that describes the object.

str: Return a string that describes the module.

str: Return a string that describes the module.

str: Return a string that describes the module.

str: Return a string that describes the module.

str: Return a string that describes the module.

str: Return a string that describes the module.

Transform predicted bbox parameters to bbox. Args: points (Tensor): Final locations of shape (N, num_query, 3) bbox_p

Transform box to the axis-aligned or rotated iou loss format. Args: bbox (Tensor): 3D box of shape (N, 6) or (N, 7). Ret

Transform box to the axis-aligned or rotated iou loss format. Args: bbox (Tensor): 3D box of shape (N, 6) or (N, 7). Ret

Function to flip images, bounding boxes, semantic segmentation map and keypoints. Add the override feature that if 'flip' is already

Network forward process. Usually includes backbone, neck and head forward without any post-processing. Args: batch_input

Network forward process. Usually includes backbone, neck and head forward without any post-processing. Args: batch_inputs

Network forward process. Usually includes backbone, neck and head forward without any post-processing. Args: batch_input

Network forward process. Usually includes backbone, neck and head forward without any post-processing. Args: batch_input

Network forward process. Usually includes backbone, neck and head forward without any post-processing. Args: batch_inputs