ScanNet data. Generate scannet infos for scannet_converter. Args: root_path (str): Root path of the raw data. split (str): S

SUNRGBD data. Generate scannet infos for sunrgbd_converter. Args: root_path (str): Root path of the raw data. split (str): S

ScanNet dataset used to generate infos for semantic segmentation task. Args: data_root (str): Root path of the raw data. ann_file

S3DIS data. Generate s3dis infos for s3dis_converter. Args: root_path (str): Root path of the raw data. split (str): Set spl

S3DIS dataset used to generate infos for semantic segmentation task. Args: data_root (str): Root path of the raw data. ann_file (

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

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

r"""NuScenes Dataset. This datset only add camera intrinsics and extrinsics to the results.

Head of DeformDETR3D. Args: with_box_refine (bool): Whether to refine the reference points in the decoder. Defaults to False.

A warpper for DGCNN-type self-attention. Args: embed_dims (int): The embedding dimension. num_heads (int): Parallel attention head

Copy the decoder in DETR transformer. Args: return_intermediate (bool): Whether to return intermediate outputs. coder_norm_cfg (di

Detr3D.

An attention module used in Detr3d. Args: embed_dims (int): The embedding dimension of Attention. Default: 256. num_h

Head of Detr3D. Args: with_box_refine (bool): Whether to refine the reference points in the decoder. Defaults to False.

Implements the Detr3D transformer. Args: as_two_stage (bool): Generate query from encoder features. Default: False. nu

Implements the decoder in DETR3D transformer. Args: return_intermediate (bool): Whether to return intermediate outputs. coder_norm

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

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

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

Base class of Multi-modality VoxelNet.

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 numbe

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

Random scale the image Args: scales

Waymo to KITTI converter. This class serves as the converter to change the waymo raw data to KITTI format. Args: load_dir (str):