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

check if model is in parallel mode.

Load annotations from ann_file. Args: ann_file (str): Path of the annotation file. Returns: list[dict]: List

Create a list of blocks of the same type that forms one ResNet stage. Args: block_class (type): a subclass of CNNBlockBa

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

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

Nms function with gpu implementation. Args: boxes (torch.Tensor): Input boxes with the shape of [N, 5] ([x1, y1, x2, y2, ry])

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

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

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

Project points in image coordinates to camera coordinates. Args: points (torch.Tensor): 2.5D points in 2D images, [N, 3], 3 c

Find the box in which each point is. Args: points (torch.Tensor): Points in shape (1, M, 3) or (M, 3), 3 dimensio

Args: predictions: return values of :meth:`forward()`. proposals (list[Instances]): proposals that match the features

Normalize, pad and batch the input images.

Preparation for a new round of evaluation. Should be called before starting a round of evaluation.

Initialize the detectron2 logger and set its verbosity level to "DEBUG". Args: output (str): a file name or a directory to save log.

Test function of point cloud branch.

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

Compute and display summary metrics for evaluation results. Note this functin can *only* be applied on the default parameter setting

Apply element-wise weight and reduce loss. Args: loss (Tensor): Element-wise loss. weight (Tensor): Element-wise weights.

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

Pillar Feature Net Layer. The Pillar Feature Net could be composed of a series of these layers, but the PointPillars paper results on

Args: optimizer, last_iter: See ``torch.optim.lr_scheduler._LRScheduler``. ``last_iter`` is the same as ``last_ep

Add shared or separable branch.

Affine transform bbox points to input image. Args: points (np.ndarray): Points to be transformed. shape: (N, 2)

Box head forward function used in both training and testing.

Args: classes (list[int] or None): scores (list[float] or None): class_names (list[str] or None): is_crowd (list[

Derive the desired score numbers from summarized COCOeval. Args: coco_eval (None or COCOEval): None represents no predic

Draw bbox on visualizer and change the color of points inside bbox3d. Args: bbox3d (numpy.array | torch.tensor, shape=[M, 7]):

Draw bbox on visualizer and change the color of points inside bbox3d. Args: bbox3d (numpy.array | torch.tensor, shape=[M, 7]):

Returns: str: module name of the caller tuple: a hashable key to be used to identify different callers

Forward logic of the keypoint prediction branch. Args: features (dict[str, Tensor]): mapping from feature map names to t

Forward logic of the mask prediction branch. Args: features (dict[str, Tensor]): mapping from feature map names to tenso

Get axis_align_matrix from info. If not exist, return identity mat. Args: info (dict): one data info term. Returns:

Utility function that scales the figure size by the map canvas size. If figsize is: - None => Return default scale.

Get affine transform matrix. Args: center (tuple): Center of current image. scale (tuple): Scale of current image.

Randomly modifies given color to produce a slightly different color than the color given. Args: color (tuple[double]): a

Rescale the output instances to the target size.

In given proto, rename all blobs with matched version

Set flag according to image aspect ratio. Images with aspect ratio greater than 1 will be set as group 1, otherwise group 0. In 3D da

mmdet will assert the type of dict/list. So convert omegaconf objects to dict/list.

Try select keys from cfg until the first key that exists. Otherwise return default.

Add bounding box to visualizer. Args: bbox3d (numpy.array, shape=[M, 7]): 3D bbox (x, y, z, x_size, y_size, z_siz

3D NMS for aligned boxes. Args: boxes (torch.Tensor): Aligned box with shape [n, 6]. scores (torch.Tensor): Scores of each box.

Run all_gather on arbitrary picklable data (not necessarily tensors). Args: data: any picklable object group: a torch proces

Generate anchors in a single range. Args: feature_size (list[float] | tuple[float]): Feature map size. It is eith

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

Applies Rotary Position Embedding to the query and key tensors. Args: q (`torch.Tensor`): The query tensor. k (`torch.Tensor`): T

Calculate nearest 3D IoU. Note: This function first finds the nearest 2D boxes in bird eye view (BEV), and then calculates the 2D

Build a box head defined by `cfg.MODEL.ROI_BOX_HEAD.NAME`.

Returns: torch.nn.Module: It now calls :func:`detectron2.modeling.build_model`. Overwrite it if you'd like a dif

Convert points in camera coordinate to lidar coordinate. Note: This function is for KITTI only. Args: points (np.ndarray, sh

Inverse function to angle2class. Args: angle_cls (torch.Tensor): Angle class to decode. angle_res (torch.Tensor): Ang

Classify each points.

See get_caffe2_inputs() below.

Convert all BatchNorm/SyncBatchNorm in module into FrozenBatchNorm. Args: module (torch.nn.Module): Returns: