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

r"""Write metrics to the tensorboard.

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

r"""Flush all meters using the current iteration.

Upsample and add two feature maps. Args: x: (Variable) top feature map to be upsampled. y: (Variable) lateral feature map. Returns

r"""Write values to tensorboard. By default, we will log the time used per iteration, time used per epoch, generator learning rate, and

r"""Write values to meters.

normals: [bz, nv, 3] lights: [bz, nlight, 6] returns: shading: [bz, nv, 3]

:param img: PIL Image :return: PIL Image

r"""Normalize using ImageNet mean and std. Args: input (4D tensor NxCxHxW): The input images, assuming to be [-1, 1]. Returns:

3x3 convolution with padding

3x3 convolution with padding

3x3 convolution with padding

3x3 convolution with padding

Convert displacement map into detail normal map

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

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

Import the module "models/[model_name]_model.py". In the file, the class called DatasetNameModel() will be instantiated. It has to be a subcl

r"""Write the value in the tensorboard. Args: step (int): Epoch or iteration number.

Flush written text to both stdout and a file, if open.

r"""Function that returns Gaussian filter coefficients. Args: kernel_size (int): filter size. It should be odd and positive. sigm

Searches for the underlying module behind the name to some python object. Returns the module and the object name (original name with module part r

Return the scheduler object. Args: opt_opt (obj): Config for the specific optimization module (gen/dis). opt (obj): PyTorch optim

INPUTS model - ['net-lin'] for linearly calibrated network ['net'] for off-the-shelf network

Ref: https://github.com/facebookresearch/pytorch3d/blob/25c065e9dafa90163e7cec873dbb324a637c68b7/pytorch3d/io/obj_io.py Load a mesh from a file-l

create a single empty directory if it didn't exist Parameters: path (str) -- a single directory path

Convert quaternion vector to angle axis of rotation. TODO: CORRECT Adapted from ceres C++ library: ceres-solver/include/ceres/rotation.h Arg

Convert quaternion coefficients to rotation matrix. Args: quat: size = [B, 4] 4 <===>(w, x, y, z) Returns: Rotation matrix cor

:param generator: :param data: { video_name: <class 'str'> source_image: <class 'torch.Tensor'> (3, 256, 256) source_

Return: coeffs_dict -- a dict of torch.tensors Parameters: coeffs -- torch.tensor, size (B, 256

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

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'.

Set updated weight and weight_mom to memory bank.

Print all variables.

r"""Get alexnet layers

r"""Creates a binary kernel to extract the patches. If the window size is HxW will create a (H*W)xHxW kernel.

r"""Return the evaluation result.

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):