r"""check if current process is the master

r"""Load network weights, optimizer parameters, scheduler parameters from a checkpoint. Args: checkpoint_path (str): Path to the c

r"""Get rank of the thread.

r"""Get world size. How many GPUs are available in this job.

r"""Save network weights, optimizer parameters, scheduler parameters to a checkpoint. Args: current_epoch (int): Current epoch.

r"""Record the value

r"""Adds an LMDB dataset to a list of datasets. Args: root (str): Path to LMDB or folder dataset. filenames: List of

r"""Return data loader . Args: cfg (obj): Global configuration file. dataset (obj): PyTorch dataset object. batch_size (i

r"""Convert numpy to torch tensor. Args: normalize (bool): Normalize image i.e. (x - 0.5) * 2. Goes from [0, 1] -

Recursively update AttrDict d with AttrDict u

r"""Set random seeds for everything, including random, numpy, torch.manual_seed, torch.cuda_manual_seed. torch.cuda.manual_seed_all is not necessa

The evaluation/inference engine. Args: data_loader: The data loader. output_dir: Output directory to dump the test res

r"""Convert all images to tensor. Args: data (dict): Dict containing data_type as key, with each value as a list

r"""Return the total loss to be backpropagated.

Return device on which model resides.

r"""Things to do after an iteration. Args: data (dict): Data used for the current iteration. current_epoch (int): Cur

Forward pass the NeRF (MLP). Args: points_3D (tensor [batch,...,3]): 3D points in world space. ray_unit (tensor [batc

r"""Get function to apply for specific op. Args: op (str): Name of the op. Returns: function handle.

Return the trainer object. Args: cfg (Config): Loaded config object. is_inference (bool): Inference mode. Returns: (

r"""Initialize distributed training

Parse arguments from command line. Syntax: --key1.key2.key3=value --> value --key1.key2.key3= --> None --key1.ke

Recursively update AttrDict d with AttrDict u with strict matching

r""" Set a model to require gradient or not. Args: model (nn.Module): Neural network model. require (bool): Whether the network r

r"""Reset the meter values

Sample n points on the view hemisphere within the angle to x. Args: anchor (tensor [...,3]): Reference 3-D unit vector on the view hemisph

r"""Set GPU affinity Args: gpu_id (int): Which gpu device.

Set the data loader corresponding to the indicated split. Args: split (str): Must be either 'train', 'val', or 'test'.

r"""Things to do before an iteration. Args: data (dict): Data used for the current iteration. current_iteration (int)

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

r"""Generic training loop. Main structure in a nutshell: for epoch in [start_epoch, end_epoch]: for batch in dataset (one

Print all variables.

r"""Calculate number of parameters in a PyTorch network. Args: model (obj): PyTorch network. Returns: (int): Number of param

r"""Collect all the state dicts from network modules to be saved.

r"""Computes required statistics about dataset. All children need to implement their own.

r"""Creates mapping from data sample idx to actual LMDB keys. All children need to implement their own. Returns: self

r"""Detach all logging variables to prevent potential memory leak.

r"""Operations to do after an epoch. Args: data (dict): Data used for the current iteration. current_epoch (int): Cur

r"""Operations to do after an iteration. Args: data (dict): Data used for the current iteration. current_epoch (int):

r"""Find key-value inputs to function from string definition. Args: function_string (str): String with function name and args. e.