Save a numpy image to the disk Parameters: image_numpy (numpy array) -- input numpy array image_path (str) -- the path o

save the current content to the HMTL file

Initialize the GANLoss class. Parameters: gan_mode (str) - - the type of GAN objective. It currently supports vanilla, lsgan, an

Initialize the GANLoss class. Parameters: gan_mode (str) - - the type of GAN objective. It currently supports vanilla, lsgan, an

Convert the range from [-1, 1] to [0, 1].

Make models eval mode during test time

Return an image from the pool. Parameters: images: the latest generated images from the generator Returns images from th

Set requies_grad=Fasle for all the networks to avoid unnecessary computations Parameters: nets (network list) -- a list of netwo

If the program could not connect to Visdom server, this function will start a new server at port < self.port >

Insert a header to the HTML file Parameters: text (str) -- the header text

add images to the HTML file Parameters: ims (str list) -- a list of image paths txts (str list) -- a list of image

Download a dataset. Parameters: save_path (str) -- A directory to save the data to. dataset (str) -- (opt

Convert label indices to one-hot vectors.

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

Compute square root of a symmetric matrix. Note that this is different from an elementwise square root. We want to compute M' where M' = sqrt(

Calculate GAN loss for the discriminator Parameters: netD (network) -- the discriminator D real (tensor array) --

Calculate GAN loss for the discriminator Parameters: netD (network) -- the discriminator D real (tensor array) --

Calculate GAN loss for the discriminator Parameters: netD (network) -- the discriminator D real (tensor array) --

Compute binary or softmax cross entropy loss.

Calculate additional output images for visdom and HTML visualization

Create a dataset given the option. This function wraps the class CustomDatasetDataLoader. This is the main interface between this package

Generate target domain labels for debugging and testing.

Create a model given the option. This function warps the class CustomDatasetDataLoader. This is the main interface between this package and '

Import the module "data/[dataset_name]_dataset.py". In the file, the class called DatasetNameDataset() will be instantiated. It has to be a s

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

Classifier distance for evaluating a generative model. This methods computes the Frechet classifier distance from activations of real imag

Return visualization images. train.py will display these images with visdom, and save the images to a HTML

Build and return a data loader.

Return a normalization layer Parameters: norm_type (str) -- the name of the normalization layer: batch | instance | none For BatchNo

Return a normalization layer Parameters: norm_type (str) -- the name of the normalization layer: batch | instance | none For BatchNo

Initialize a network: 1. register CPU/GPU device (with multi-GPU support); 2. initialize the network weights Parameters: net (network)

Initialize a network: 1. register CPU/GPU device (with multi-GPU support); 2. initialize the network weights Parameters: net (network)

Kernel "classifier" distance for evaluating a generative model. This methods computes the kernel classifier distance from activations of r

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

Parse our options, create checkpoints directory suffix, and set up gpu device.

Print out the network information.

Reset the gradient buffers.

Restore the trained generator and discriminator.

Unpack input data from the dataloader and perform necessary pre-processing steps. Parameters: input (dict): includes the data its

Load and print networks; create schedulers Parameters: opt (Option class) -- stores all the experiment flags; needs to be a subcl

Fix InstanceNorm checkpoints incompatibility (prior to 0.4)

Print warning information about image size(only print once)

Calculate GAN loss for discriminator D_A

Calculate GAN loss for discriminator D_A

Calculate GAN loss for discriminator D_A

Calculate GAN loss for discriminator D_B

Calculate GAN loss for discriminator D_B

Calculate GAN loss for discriminator D_B

Calculate the loss for generators G_A and G_B

Calculate the loss for generators G_A and G_B

Calculate the loss for generators G_A and G_B

Construct a convolutional block. Parameters: dim (int) -- the number of channels in the conv layer. padding

Construct a convolutional block. Parameters: dim (int) -- the number of channels in the conv layer. padding

Create a generator and a discriminator.

Build a tensorboard logger.

Display current results on visdom; save current results to an HTML file. Parameters: visuals (OrderedDict) - - dictionary of imag

Run forward pass; called by both functions <optimize_parameters> and <test>.

Run forward pass; called by both functions <optimize_parameters> and <test>.

Run forward pass; called by both functions <optimize_parameters> and <test>.

Run forward pass; called by both functions <optimize_parameters> and <test>.

Initialize our parser with basic options(only once). Add additional model-specific and dataset-specific options. These options are def

Return traning losses / errors. train.py will print out these errors on console, and save them to a file

Return the directory that stores images

Return image paths that are used to load current data

Create label tensors with the same size as the input. Parameters: prediction (tensor) - - tpyically the prediction from a discrim

Create label tensors with the same size as the input. Parameters: prediction (tensor) - - tpyically the prediction from a discrim

Compute gradient penalty: (L2_norm(dy/dx) - 1)**2.

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