r"""Generating random camera pose in the upper hemisphere, in the format of origin-direction-up Assuming [Y X Z] coordinate. Y is negative gravity

r"""Generating random camera pose in the upper hemisphere, in the format of origin-direction-up

r"""Attempting to solve the camera too close to wall problem and the lack of aerial poses.

r"""Produces a new cam_c so that the effect of rendering with the new cam_c and target_res is the same as rendering with the old parameters and th

r"""Randomly shift the input tensor. Args: x (4D tensor): The input batch of images. offset (int): The maximum offset ratio that

r"""Update the statistics in the moving average model. Args: data_loader (torch.utils.data.DataLoader): Data loader for

r"""Reset batch norm statistics Args: m: Pytorch module

Recursively find object and set value

r""" Make best effort to sample points within the same distance for every ray. Exception: When there is not enough voxel. Args: de

r"""Save intermediate training results for debugging purpose. Args: visualization_images (tensor): Image where pixel values are in [-1, 1

r"""Convert a 3 dimensional torch tensor to a PIL image with the desired width and height. Args: filename (str): Image filename to be

r"""Smooth interpolation of segmentation maps. Args: x (4D tensor): Segmentation maps. size(2D list): Target size (H,

r"""Performs a single optimization step. Args: closure (callable, optional): A closure that reevaluates the model

r"""Get Driver Version

r"""Convert flow tensor to color image. Args: tensor (tensor) of If tensor then (NxCxHxW) or (NxTxCxHxW) or (CxHxW). imty

r"""Compute results images for a batch of input data and save the results in the specified folder. Args: data_loader (tor

r"""Compute results images for a batch of input data and save the results in the specified folder. Args: data_loader (tor

r"""Move all tensors inside data to cpu. Args: data (dict, list, or tensor): Input data.

r"""Move all floats to half. Args: data (dict, list or tensor): Input data.

r"""Anneal k after each epoch.

r"""3-dimensional Homogeneous matrix and regular vector multiplication Convert v to homogeneous vector, perform M-V multiplication, and convert ba

r"""Weight demodulation.

r"""Simple function wrapper for the master function

Convert object to yaml dict and return.