r"""Returns a string that holds a printable representation of an object

r"""Sample points along rays, forwarding the per-point MLP and aggregate pixel features Args: blk_feats (K x C1 tensor): Sparse b

r"""Get difference between two lists of tensors or two tensors. Args: a: list of tensors or tensor b: lis

r"""Return output values. Note that when the gan mode is relativistic. It will do the difference before returning. Args: n

r"""Return the total loss to be backpropagated. Args: gen_forward (bool): If ``True``, backpropagates the generator loss,

r"""Compute visualization image. Args: data (dict): The current batch.

r"""Get attribute.

r"""Initialize loss terms. Args: cfg (obj): Global configuration.

r"""Model specific custom start of iteration process. We will do two things. First, put all the data to GPU. Second, we will resize the

r"""Applies differentiable augmentation. Args: data (dict): Input data. keys (list of str): Keys to the data values that we want t

r"""Calculate height map given a voxel grid [Y, X, Z] as input. The height is defined as the Y index of the surface (non-air) block Args:

r"""Calibrate batch norm momentum Args: m: Pytorch module

r"""Copy the original weights to the moving average weights.

r"""Get number of devices

r"""Compute the loss for GANcraft discriminator. Args: data (dict): Training data at the current iteration.

r""" gather to all ranks

r""" Reduce to rank 0

r"""Download a file from google drive. Args: URL: GDrive file ID. destination: Path to save the file. Returns:

CUDA vector math functions

r"""PyTorch module forward function overload.