r"""Returns a new tensor with boolean elements representing if each element is `+/-INF` or not. Arguments: tensor (Tensor): A tensor

r"""Returns a new tensor with boolean elements representing if each element is `NaN` or not. Arguments: tensor (Tensor): A tensor to

r""" Load a dictionnary describing the attributes of each image in the dataset and save the list of all the possible attributes and th

r""" Load a given checkpoint. Args: - pathModel (string): path to the file containing the model

r""" Add a minibatch standard deviation channel to the current layer. In other words: 1) Compute the standard deviation of the feature

r""" Save the model basic configuration (the part that doesn't change with the training's progression) at the given path

r""" Save a checkpoint at the given directory. Please note that the basic configuration won't be saved. This function produce

r""" Update the value of the merging factor alpha Args: - alpha (float): merging factor, must be in [0, 1]

r""" Train the model on one epoch. Args: - dbLoader (DataLoader): dataset on which the training will be made

r""" Update the blending factor alpha. Args: - alpha (float): blending factor (in [0,1]). 0 means only the

r""" Update the object config with new inputs. Args: config (dict or BaseConfig) : fields of configuration to be updated

r""" Args: - pathdb (string): path to the directorty containing the image dataset - use

r""" Args: Specific Arguments: - depthScale0 (int) - initBiasToZero (bool): should layer's bias be initialize

r""" Args: dimLatentVector (int): dimension of the latent vector in the model dimOutput (int): number of channels of t

r""" Build a discriminator for a progressive GAN model Args: - depthScale0 (int): depth of the lowest resolution scales

r""" equalized (bool): if true, the layer's weight should evolve within the range (-1, 1) initBiasToZero (boo

r""" A nn.Conv1d module with specific constraints Args: nChannelsPrevious (int): number of channels in the previous layer

r""" A nn.Conv2d module with specific constraints Args: nChannelsPrevious (int): number of channels in the previous layer

r""" A nn.Linear module with specific constraints Args: nChannelsPrevious (int): number of channels in the previous layer