Initialize network weights. Parameters: net (network) -- network to be initialized init_type (str) -- the name of an initializa

Define the common options that are used in both training and test.

Load all the networks from the disk. Parameters: epoch (int) -- current epoch; used in the file name '%s_net_%s.pth' % (epoch, na

Calculate losses, gradients, and update network weights; called in every training iteration

display the current losses on visdom display: dictionary of error labels and values Parameters: epoch (int) -- current

Preprocess the CelebA attribute file.

print current losses on console; also save the losses to the disk Parameters: epoch (int) -- current epoch iters (int

Print the total number of parameters in the network and (if verbose) network architecture Parameters: verbose (bool) -- if verbos

Print and save options It will print both current options and default values(if different). It will save options into a text file / [

Reset the self.saved status

Save images to the disk. Parameters: webpage (the HTML class) -- the HTML webpage class that stores these imaegs (see html.py for more de

Add scalar summary.

Translate images using StarGAN trained on a single dataset.

Forward function used in test time. This function wraps <forward> function in no_grad() so we don't save intermediate steps for backprop

Find the trace of the positive sqrt of product of covariance matrices. '_symmetric_matrix_square_root' only works for symmetric matrices, so we

Train StarGAN within a single dataset.

Update learning rates for all the networks; called at the end of every epoch

Decay learning rates of the generator and discriminator.

Calculate loss given Discriminator's output and grount truth labels. Parameters: prediction (tensor) - - tpyically the prediction

Calculate loss given Discriminator's output and grount truth labels. Parameters: prediction (tensor) - - tpyically the prediction

Return a data point and its metadata information. Parameters: index - - a random integer for data indexing Returns:

Return a data point and its metadata information. Parameters: index (int) -- a random integer for data indexing Ret

Return one image and its corresponding attribute label.

Initialize the class; save the options in the class Parameters: opt (Option class)-- stores all the experiment flags; needs to be

Initialize this class Step 1: create a dataset instance given the name [dataset_mode] Step 2: create a multi-threaded data loader.

Initialize this dataset class. Parameters: opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseO

Reset the class; indicates the class hasn't been initailized

Initialize configurations.

Initialize summary writer.

Initialize and preprocess the CelebA dataset.

Initialize the CycleGAN class. Parameters: opt (Option class)-- stores all the experiment flags; needs to be a subclass of BaseOpt

Construct a Resnet-based generator Parameters: input_nc (int) -- the number of channels in input images output_n

Initialize the Resnet block A resnet block is a conv block with skip connections We construct a conv block with build_conv_block func

Construct a Unet generator Parameters: input_nc (int) -- the number of channels in input images output_nc (int) -- th

Construct a Unet submodule with skip connections. Parameters: outer_nc (int) -- the number of filters in the outer conv layer

Construct a PatchGAN discriminator Parameters: input_nc (int) -- the number of channels in input images ndf (int)

Construct a 1x1 PatchGAN discriminator Parameters: input_nc (int) -- the number of channels in input images ndf (int

Initialize the BaseModel class. Parameters: opt (Option class)-- stores all the experiment flags; needs to be a subclass of BaseO

Initialize the CycleGAN class. Parameters: opt (Option class)-- stores all the experiment flags; needs to be a subclass of BaseOpt

Construct a Resnet-based generator Parameters: input_nc (int) -- the number of channels in input images output_n

Initialize the Resnet block A resnet block is a conv block with skip connections We construct a conv block with build_conv_block func

Construct a Unet generator Parameters: input_nc (int) -- the number of channels in input images output_nc (int) -- th

Construct a Unet submodule with skip connections. Parameters: outer_nc (int) -- the number of filters in the outer conv layer

Construct a PatchGAN discriminator Parameters: input_nc (int) -- the number of channels in input images ndf (int)

Construct a 1x1 PatchGAN discriminator Parameters: input_nc (int) -- the number of channels in input images ndf (int

Initialize the HTML classes Parameters: web_dir (str) -- a directory that stores the webpage. HTML file will be created at <web_d

Initialize the Visualizer class Parameters: opt -- stores all the experiment flags; needs to be a subclass of BaseOptions

Initialize the ImagePool class Parameters: pool_size (int) -- the size of image buffer, if pool_size=0, no buffer will be created

Return a batch of data

Return the total number of images in the dataset.

Return the number of data in the dataset

Return the total number of images in the dataset. As we have two datasets with potentially different number of images, we take a maxi

Return the number of images.

Calculate the gradient penalty loss, used in WGAN-GP paper https://arxiv.org/abs/1704.00028 Arguments: netD (network) -- dis

Calculate the gradient penalty loss, used in WGAN-GP paper https://arxiv.org/abs/1704.00028 Arguments: netD (network) -- dis

Compute the ith block of the KID estimate.

Create a discriminator Parameters: input_nc (int) -- the number of channels in input images ndf (int) -- the number

Create a discriminator Parameters: input_nc (int) -- the number of channels in input images ndf (int) -- the number

Create a generator Parameters: input_nc (int) -- the number of channels in input images output_nc (int) -- the number of channels

Create a generator Parameters: input_nc (int) -- the number of channels in input images output_nc (int) -- the number of channels

Calculate and print the mean of average absolute(gradients) Parameters: net (torch network) -- Torch network name (str) -- the na

Standard forward

Forward function (with skip connections)

Standard forward