Gets the current evaluation result. Returns ------- metrics : tuple of float pixAcc and mIoU

Creates a dataset with the specified parameters. Args: dataset_str: A dataset string description (e.g. ImageNet:split=TRAIN).

Dump model and checkpointables to a file. Args: name (str): name of the file. kwargs (dict): extra arbitrary

Updates the internal evaluation result. Parameters ---------- labels : 'NumpyArray' or list of `NumpyArray` The l

Function to transform Isotropic Gaussians from world frame to camera frame. Args: params: dict of parameters time_idx: t

Creates a data loader with the specified parameters. Args: dataset: A dataset (third party, LaViDa or WebDataset). batch_siz

Setup logging. Args: output: A file name or a directory to save log files. If None, log files will not be saved. If outp

Returns: True if distributed training is enabled

Create configs and perform basic setups.

r"""Convert a set of points to homogeneous coordinates. Args: pts (torch.Tensor): Tensor containing points to be homogenized. Shape:

r"""Function that computes the relative homogenous transformation from a reference transformation :math:`T_1^{0} = \begin{bmatrix} R_1 & t_1 \\

Get matrix representation of intrinsics.

Input : gt_traj: list of 4x4 matrices est_traj: list of 4x4 matrices len(gt_traj) == len(est_traj)

this will perform the index select, cat the tensors, and provide the attn_bias from cache

Returns: The rank of the current process within the global process group.

Returns: The number of processes in the process group

Loads config file. Args: path (str): path to config file. default_path (str, optional): whether to use default path. Default

r"""Transforms a set of points `pts_b` from frame `b` to frame `a`, given an SE(3) transformation matrix `t_ab` Args: pts_b (torch.Te

r"""Convert a set of points from homogeneous coordinates to Euclidean coordinates. This is usually done by taking each point (x, y, z, w) and