Calculate the yaw angle from a quaternion. Note that this only works for a quaternion that represents a box in lidar or global coordinate fra

Rename the op_id-th operator in predict_net, change it's output_id-th input's name to the new_name. It also does automatic re-route and c

Resets the currently set image.

If `resume==True` and `cfg.OUTPUT_DIR` contains the last checkpoint (defined by a `last_checkpoint` file), resume from the file. Resu

Rotate boxes with points (optional) with the given angle or rotation matrix. Args: angles (float | torch.Tensor | np.ndar

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

r"""Randomly sample seeds from all imvotes. Modified from `<https://github.com/facebookresearch/imvotenet/blob/a8856345146bacf29a57266a2f0b874406

Given a list of N Instances (for N images), each containing a `gt_classes` field, return a list of Instances that contain only instances with

Sets the MetricData entry for a certain detection_name and match_distance.

Setup multi-processing environment variables.

Test without augmentation, stage 2. Args: points (list[torch.Tensor], optional): Elements in the list should have

Test without augmentation.

Test function of point cloud branch.

RPN test function.

Updates the underlying post processor with the current `bos_token` and `eos_token`.

Call function to apply noise to each ground truth in the scene. Args: input_dict (dict): Result dict from loading pipeline.

Call function to collect keys in results. The keys in ``meta_keys`` will be converted to :obj:`mmcv.DataContainer`. Args:

Args: kernel_size (Tuple): kernel size of the projection layer. stride (Tuple): stride of the projection layer.

Multi-Scale Deformable Attention Module :param d_model hidden dimension :param n_levels number of feature levels

Args: bottom_up (Backbone): module representing the bottom up subnetwork. Must be a subclass of :class:`Backbone`

NOTE: this interface is experimental. Args: num_classes (int): number of foreground classes (i.e. background is not incl

Args: cfg (CfgNode): torch_model (nn.Module): the detectron2 model (meta_arch) to be converted.

int: Number of points in the current object.

Add shared or separable branch. Args: in_channels (int): Input feature channel. conv_channels (tuple): Middle feature

Assert that each stride is 2x times its preceding stride, i.e. "contiguous in log2".

Naive tracking heuristics to assign same color to the same instance, will update the internal state of tracked instances. Re

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

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

Execute inference on a list of inputs, using batch size = self.batch_size, instead of the length of the list. Inputs & outpu

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

Forward function of roi_extractor and bbox_head used in both training and testing. Args: features (torch.Tensor): Backbon

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

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

Initialize conv layers of a single level head.

Caffe2 implementation of preprocess_image, which is called inside each MetaArch's forward. It normalizes the input images, and the fi

Calculate proper im2col step size, which should be divisible by input_size and not larger than prefer_size. Meanwhile the step size s

Returns: bool: whether the arguments contain CfgNode and should be considered forwarded to from_config.

Perform clipping on polygons that are partially behind the camera. This method is necessary as the projection does not work for point

Run `_decode_per_level_predictions` for all feature levels and concat the results.

Retrieve object orientation. Args: ori_vector (Tensor): Local orientation in [sin, cos] format. shape: (N, 2)

Transform anchors into proposals by applying the predicted anchor deltas. Returns: proposals (list[Tensor]): A list of L

Find proper places to draw text given a binary mask.

Apply EMA update to `self.name` using `value`. This is mainly used for loss normalizer. In Detectron1, loss is normalized by number

Evaluate the coco results using COCOEval API.

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 nuScenes protocol. Args: result_path (str): Path of the result file. logger (logging

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

Extract inputs from features dictionary. Args: feat_dict (dict): Feature dict from backbone. Returns: torch.

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

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