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.

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.

Print out the network information.

Reset the gradient buffers.

Reset the gradient buffers.

Restore the trained generator and discriminator.

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

Vanilla Attack.

Vanilla Attack.

Vanilla Attack.

Vanilla Attack.

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.

Create a generator and a discriminator.

Create a generator and a discriminator.

Create a generator and a discriminator.

Build a tensorboard logger.

Build a tensorboard logger.

Build a tensorboard logger.

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