r"""Every trainer should implement its own model forward.

r"""Perform data augmentation on images only. Args: data (dict): Keys are from data types. Values can be numpy.ndarray

Recursively print the configuration (with termcolor).

Render the rays given the camera intrinsics and poses. Args: pose (tensor [batch,3,4]): Camera poses ([R,t]). intr (t

Render the rays given the camera intrinsics and poses. Args: pose (tensor [batch,3,4]): Camera poses ([R,t]). intr (t

Recursively find object and return value

Save the final configuration to a yaml file.

r"""Return the networks. We will first set the random seed to a fixed value so that each GPU copy will be initialized to have the same network

r"""Return the optimizers. The following objects are constructed as class members: - optim (obj): Model optimizer object.

r"""Return the schedulers. The following objects are constructed as class members: - sched (obj): Model optimizer scheduler object.

r"""Reshape weight to obtain the matrix form. Args: weight (Parameters): pytorch layer parameter tensor.

r"""Things to do before an epoch. Args: current_epoch (int): Current number of epoch.

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

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

r"""One training step. Args: data (dict): Data used for the current iteration.

r"""Update the moving average.

r"""Initialize weights in the network. Args: init_type (str): The name of the initialization scheme. gain (float): The parameter

r"""Wrap the networks with AMP DDP and (optionally) model average. Args: cfg (obj): Global configuration. model (obj): Model obje

Utility function for write summary to log_writer.

Convert object to yaml dict and return.

Process raw data and return processed data in a dictionary. Args: idx: The index of the sample of the dataset. Returns: A

Process raw data and return processed data in a dictionary. Args: idx: The index of the sample of the dataset. Returns: A

Process raw data and return processed data in a dictionary. Args: idx: The index of the sample of the dataset. Returns: A

r"""Entry function for dataset.

Initialize a multi-layer perceptron with skip connection. Args: layer_dims: A list of integers representing the number of channels

Initialize a multi-layer perceptron with skip connection. Args: layer_dims: A list of integers representing the number of channels

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

r"""Compute visualization outputs. Args: data (dict): Data used for the current iteration.