r""" Args: attribKeysOrder (dict): dictionary containing the all the possible categories of t

r""" Args: - pathdb (string): path to the directorty containing the image dataset. - useGPU (bool): set to

r""" Add a new scale to the model. The output resolution becomes twice bigger.

r""" Build a 8bits mask that split a full input latent vector into two intermediate latent vectors: one for the shape network and one for the

Applies fade out at the end of an audio vector x

r""" Given an input tensor and its targeted status (detected as real or detected as fake) build the associated loss Args:

r""" Compute the conditional loss between the network's output and the target. This loss, L, is the sum of the losses Lc of the catego

r""" Get output image size (W, H)

r""" Initialize the GAN model.

Function that initializes the transformation pipeline Args: transform (str): name of the transformation

:param d: (num_samples x, num_samples y) :param var: :return:

r""" A dirty hack to load a module from a string input Args: package (string): package name name (string): module name R

r""" Update the discrimator D using the given "real" inputs. Args: input (torch.tensor): input batch of real data

r""" Parse a file name with the given pattern: pattern = ($model_name)_train_config.json Raise an error if the pattern doesn't match

Call in a loop to create terminal progress bar @params: iteration - Required : current iteration (Int) total - Requi

r""" Load a permanent configuration describing a models. The variables described in this file are constant through the training.