r"""PyTorch module forward function overload.

r"""PyTorch module forward function overload.

r""" Forward network Args: x (N x H x W x M x in_channels tensor): Projected features. raydir (N x H x W x 1 x viewdi

r"""GAN loss computation. Args: input_x (tensor or list of tensors): Output values. t_real (boolean): Is this output

r"""GANcraft discriminator forward. Args: data (dict): - data (N x C1 x H x W tensor) : Ground truth images.

r""" Args: x (tensor): Input tensor. cond_inputs (list of tensors) : Conditional input tensors. kw_cond_i

r""" Args: x (tensor): Input tensor. noise (tensor, optional, default=``None``) : Noise tensor to be

r""" Args: x (tensor): Input tensor.

r"""Adaptive Normalization forward. Args: x (N x C1 x * tensor): Input tensor. y (N x C2 tensor): Conditional informa

r"""Spatially Adaptive Normalization (SPADE) forward. Args: x (N x C1 x H x W tensor) : Input tensor. cond_inputs (li

r"""Spatially Adaptive Normalization (SPADE) forward. Args: x (4D tensor) : Input tensor. cond_inputs (list of tensor

r""" Args: x (tensor): Input tensor.

r""" Args: x (tensor) : input feature maps (B X C X W X H) Returns: (tuple): - out (tensor) : s

r""" Args: x (tensor): Input tensor. cond_inputs (list of tensors) : Conditional input tensors. kw_cond_i

r""" Args: x (tensor): Input tensor. cond_inputs (list of tensors) : Conditional input tensors. mask_in (

r""" Args: x (tensor): Input tensor. cond_inputs (list of tensors) : Conditional input tensors. kw_cond_i

r""" Args: x (tensor): Input tensor. mask_in (tensor, optional, default=``None``) If not ``None``, it

r""" Args: x (tensor): Input tensor. mask_in (tensor, optional, default=``None``) If not ``None``, it

r""" Args: x (tensor): Input tensor. cond_inputs (list of tensors) : Conditional input tensors. do_checkp

r""" Args: x (tensor): Input tensor. cond_inputs (list of tensors) : Conditional input tensors. conv_weig

r""" Args: x (tensor) : Input tensor. cond_inputs (list of tensors) : conditional input. Returns:

r"""Implementation of the up residual block forward function. If the order is 'NAC' for the first residual block, we will first do the

r""" Args: x (tensor): Input tensor. cond_inputs (list of tensors) : Conditional input tensors. mask_in (

r""" Args: x (tensor): Input tensor. cond_inputs (list of tensors) : Conditional input tensors. Returns:

r"""Weight demodulation forward

r"""SceneDreamer forward.

r"""SPADE Generator forward. Args: data (dict): - images (N x C1 x H x W tensor) : Ground truth images

r"""SPADE Generator forward. Args: data (dict): - data (N x C1 x H x W tensor) : Ground truth images.

r"""SPADE Style Encoder forward. Args: input_x (N x 3 x H x W tensor): input images. Returns: (tuple):

r""" Forward network Args: x (N x H x W x M x in_channels tensor): Projected features. raydir (N x H x W x 1 x viewdi

r""" Forward network Args: z (N x style_dim tensor): Style codes.

r"""Forward network Args: x (... x in_channels tensor): Ray direction embeddings. z (... x style_dim tensor): Style c

r"""Forward network. Args: x (N x in_channels x H x W tensor): Intermediate feature map z (N x style_dim tensor): Sty

r"""SPADE Style Encoder forward. Args: input_x (N x 3 x H x W tensor): input images. Returns: mu (N x C tenso

r"""Return the target vector for the binary cross entropy loss computation. Args: fake_features (list of lists): Discrimin

r"""Return weighted MSE Loss. Args: input (tensor): target (tensor): weight (tensor): Returns:

r"""Compute loss Args: mu (tensor): mean logvar (tensor): logarithm of variance

r"""GAN loss computation. Args: dis_output (tensor or list of tensors): Discriminator outputs. t_real (bool): If ``Tr

r"""Perceptual loss forward. Args: inp (4D tensor) : Input tensor. target (4D tensor) : Ground truth tensor, same shape

r"""Extract perceptual features.

r"""Converting voxel center array to voxel corner array. The size of the produced array grows by 1 on every dimension. Args: voxel (t

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

r"""Get obect name

r"""Get attribute with default choice. If attribute does not exist, set it using the default value. Args: cfg (obj) : Config options.

r"""Get the checkpoint path. If it does not exist yet, download it from the url. Args: checkpoint_path (str): Checkpoint path.

r"""Get number of classes for class-conditional GAN model Args: data_cfg (obj): Data configuration structure. Returns: (int)

List dirs immediately under input_dir. Args: input_dir (str): Directory to list children of. Returns: (list): List of dir

r"""Iteratively try to get the attribute from cfg. If not found, return default. Args: cfg (obj): Config file. attr_name (str

List dirs recursively under input_dir. Args: input_dir (str): Directory to list children of. ext (str): Extension of files expect

r"""Return dataset objects for testing Args: cfg (obj): Global configuration file. Returns: (obj): Val data loader. It may n

r"""Get weight state Args: mod: Pytorch module

r"""Return the gradient norm of model. Args: model (PyTorch module): Your network.

r"""Compute result images according to the provided camera trajectory and save the results in the specified folder. The full image is evaluate

r"""Init function Args: m: module to be weight initialized.

r"""loc: [2]: x, z.

r"""loc: [2]: x, z.

r"""Load network weights, optimizer parameters, scheduler parameters from a checkpoint. Args: cfg (obj): Global configura

r"""Load keys from lmdb handles. Args: keys (dict): This has data_type as key, and a list of paths as values. handles

r"""Load keys from lmdb handles. Args: keys (dict): This has data_type as key, and a list of paths into LMDB as values.

r"""Load keys from AWS S3 handles. Args: keys (dict): This has data_type as key, and a list of paths as values. handl

r"""Convert appropriate image data types to one-hot representation. Args: data (dict): Dict containing data_type as key, with each value

r"""Apply this function only to the master GPU.

r"""master-only print

r"""Entry point for augmentation. Args: inputs (dict): Keys are from self.augmentable_data_types. Values are list

r"""Plot keypoints on image. Args: image (PIL.Image, or numpy.ndarray, or torch.Tensor): Input image. keypoints (np.ndarray or torc

r"""Plot keypoints on black image. Args: resize_h (int): Height to be resized to. resize_w (int): Width to be resized to.