Parameters ---------- vecs: Iterable[np.ndarray] Iterable of 10D pose representation. intrinsics: np.nda

During inference, the functionary of batch norm layers is turned off but only the mean and var alone channels are used, which exposes the chance t

Get the 2D annotation records for a given info. Args: info: Information of the given sample data. occluded: Integer (0, 1, 2, 3)

Get available scenes from the input nuscenes class. Given the raw data, get the information of available scenes for further info generation.

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

Get the reference points used in SCA and TSA. Args: H, W: spatial shape of bev. Z: hight of pillar. D: sam

Returns a new Transform3d object that represents an inverse of the current transformation. Args: invert_composed

Prepare data related to Lyft dataset. Related data consists of '.pkl' files recording basic infos. Although the ground truth database and 2D

Convert the output to the box class in the nuScenes. Args: detection (dict): Detection results. - boxes_3d (:obj:`BaseInstance

Get the intersection of the convex hull of the reprojected bbox corners and the image canvas, return None if no intersection. Args: c

Prepare data for testing. Args: index (int): Index for accessing the target data. Returns: dict: Testing dat

Parse and save the images in png format. Args: frame (:obj:`Frame`): Open dataset frame proto. file_idx (int): Curren

Test function without augmentaiton.

Smooth L1 loss defined in the Fast R-CNN paper as: | 0.5 * x ** 2 / beta if abs(x) < beta smoothl1(x) = |

The iteration step during training. This method defines an iteration step during training, except for the back propagation and optimi

convert sample queue into one single sample.

In BEVFormer_fp16, we use this `val_step` function to inference the `prev_pev`. This is not the standard function of `val_step`.

Initialize a DetectionEval object. :param nusc: A NuScenes object. :param config: A DetectionConfig object. :param re

An equivalent of `torch.as_tensor`, but works under tracing if input is a list of tensor. `torch.as_tensor` will record a constant in tracing

Return the rotation matrices for one of the rotations about an axis of which Euler angles describe, for each value of the angle given. A

Build the default pipeline for this dataset.

Determine if R is a valid rotation matrix by checking it satisfies the following conditions: ``RR^T = I and det(R) = 1`` Args:

Parameters ---------- box1, box2: (x1, y1, x2, y2)

Convert class_id in loaded segmentation mask to label.

Convert class_id in loaded segmentation mask to label.

Load data using input pipeline and extract data according to key. Args: index (int): Index for accessing the target data.

Generate the train/val infos from the raw data. Args: nusc (:obj:`NuScenes`): Dataset class in the nuScenes dataset. train_scenes

Generate the train/val infos from the raw data. Args: lyft (:obj:`LyftDataset`): Dataset class in the Lyft dataset. train_scenes

Return the inverse of self._matrix.

Get data loading pipeline in self.show/evaluate function. Args: pipeline (list[dict] | None): Input pipeline. If None is given, \

Helper function for building a rotation function using angles. The output is always of shape (N,). The input can be one of: - To

Index instance tokens for uniquely identifying instances across samples

Initialize classification branch and regression branch of head.

Pad images according to ``self.size``.

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

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

Fast determinant calculation for a batch of 3x3 matrices. Note, result of this function might not be the same as `torch.det()`. The diff

Returns torch.sqrt(torch.max(0, x)) but with a zero subgradient where x is 0.

Parameters ---------- quat: Tensor (N, 4). Batch of (allocentric) quaternions. proj_ctr: Tensor (N, 2). Projected ce

Create an :class:`Instances` object used by the models, from instance annotations in the dataset dict. Args: annos (list[dict]):

Computes one-to-one matching based on the weighted costs. This method assign each query prediction to a ground truth or background. Th

Create a 1D, 2D, or 3D average pooling module.

Build data config for loading visualization data.

Convert transformation matrix in Cartesian coordinates to homogeneous format. Args: mat (np.ndarray): Transformation matr

Check if a box is visible inside an image without accounting for occlusions. :param box: The box to be checked. :param intrinsic: <float:

Plot the true positive curve for the specified class. :param md_list: DetectionMetricDataList instance. :param metrics: DetectionMetrics

Convert keys in pycls pretrained RegNet models to mmdet style.