Points of instances in LIDAR coordinates. Args: tensor (torch.Tensor | np.ndarray | list): a N x points_dim matrix. points_dim (i

BBox3DL1Cost. Args: weight (int | float, optional): loss_weight

Base class of Multi-modality VoxelNet.

Base class of Multi-modality VoxelNet.

Base class of Multi-modality VoxelNet.

Crop the image Args: size (tuple, optional): Fixed padding size.

Head of DeformDETR3DCam. Args: with_box_refine (bool): Whether to refine the reference points in the decoder. Defaults to

r"""Feature Pyramid Network. This is an implementation of paper `Feature Pyramid Networks for Object Detection <https://arxiv.org/abs/1612.031

Base class of Multi-modality VoxelNet.

An attention module used in Deformable-Detr. `Deformable DETR: Deformable Transformers for End-to-End Object Detection. <https://arxiv.org/p

Implements the DeformableDETR transformer. Args: num_feature_levels (int): Number of feature maps from FPN: Default: 4.

Implements the decoder in DETR transformer. Args: return_intermediate (bool): Whether to return intermediate outputs. coder_norm_c

Switch the mode of YOLOX during training. This hook turns off the mosaic and mixup data augmentation and switches to use L1 loss in bbox_hea

Apply global rotation, scaling and translation to a 3D scene. - adding support for both lidar and radar points Args: rot_range (list[floa

Computes one-to-one matching between predictions and ground truth. This class computes an assignment between the targets and the predictions

Fuse feature maps from lidar and radar

Load radar points from multiple sweeps. This is usually used for nuScenes dataset to utilize previous sweeps. Args: sweeps_num (int

Load radar points from multiple sweeps. This is usually used for nuScenes dataset to utilize previous sweeps. Args: sweeps_num (int

Load Points From File. Load sunrgbd and scannet points from file. Args: coord_type (str): The type of coordinates of points cloud.

Load points from multiple sweeps. This is usually used for nuScenes dataset to utilize previous sweeps. Args: sweeps_num (int): Num

Test-time augmentation with multiple scales and flipping. Args: transforms (list[dict]): Transforms to apply in each augmentation.

Bbox coder for NMS-free detector. Args: pc_range (list[float]): Range of point cloud. post_center_range (list[float]): Limit of

Bbox coder for NMS-free detector. Args: pc_range (list[float]): Range of point cloud. post_center_range (list[float]): Limit of

Normalize the image. Added key is "img_norm_cfg". Args: mean (sequence): Mean values of 3 channels. std (sequence): Std va

r"""NuScenes Dataset. This class serves as the API for experiments on the NuScenes Dataset. Please refer to `NuScenes Dataset <https://www.n

Pad the multi-view image. There are two padding modes: (1) pad to a fixed size and (2) pad to the minimum size that is divisible by some num

Apply photometric distortion to image sequentially, every transformation is applied with a probability of 0.5. The position of random contrast is

Apply global rotation, scaling and translation to a 3D scene. Args: rot_range (list[float]): Range of rotation angle. Def

Flip the points & bbox. If the input dict contains the key "flip", then the flag will be used, otherwise it will be randomly decided by a

Get radar points to new radar points.

Flip the points & bbox. If the input dict contains the key "flip", then the flag will be used, otherwise it will be randomly decided by a rat

Random scale the image Args: scales

Class for sampling data from the ground truth database. Args: info_path (str): Path of groundtruth database info. data_root (st

Fuse lidar and radar points.