Discriminator network with PatchGAN.

Generator network.

This class implements an image buffer that stores previously generated images. This buffer enables us to update discriminators using a history of

Defines the Unet submodule with skip connection. X -------------------identity---------------------- |-- downsampling -- |submodule| -

Defines the Unet submodule with skip connection. X -------------------identity---------------------- |-- downsampling -- |submodule| -

Tensorboard logger.

Discriminator network with PatchGAN.

Generator network.

Defines a PatchGAN discriminator

Defines a PatchGAN discriminator

Residual Block with instance normalization.

Resnet-based generator that consists of Resnet blocks between a few downsampling/upsampling operations. We adapt Torch code and idea from Justin

Resnet-based generator that consists of Resnet blocks between a few downsampling/upsampling operations. We adapt Torch code and idea from Justin

Create a Unet-based generator

Create a Unet-based generator

Dataset class for the CelebA dataset.

Dataset class for the CelebA dataset.

Wrapper class of Dataset class that performs multi-threaded data loading

This HTML class allows us to save images and write texts into a single HTML file. It consists of functions such as <add_header> (add a text head

Dataset class for the CelebA dataset.

Tensorboard logger.

Defines a 1x1 PatchGAN discriminator (pixelGAN)

Defines a 1x1 PatchGAN discriminator (pixelGAN)

Residual Block with instance normalization.

Define a Resnet block

Define a Resnet block

Solver for training and testing StarGAN.

Solver for training and testing StarGAN.

Solver for training and testing StarGAN.

This class includes test options. It also includes shared options defined in BaseOptions.

This class includes training options. It also includes shared options defined in BaseOptions.

This class includes several functions that can display/save images and print/save logging information. It uses a Python library 'visdom' for disp

Average Smoothing 2D. :param channels: number of channels in the output. :param kernel_size: aperture size.

Average Smoothing 2D. :param channels: number of channels in the output. :param kernel_size: aperture size.

Generator network.

This class is an abstract base class (ABC) for datasets. To create a subclass, you need to implement the following four functions: -- <__init

This class is an abstract base class (ABC) for models. To create a subclass, you need to implement the following five functions: -- <__ini

This class defines options used during both training and test time. It also implements several helper functions such as parsing, printing, and sa

Conv Smoothing 2D. :param kernel_size: size of the convolving kernel.

Conv Smoothing 2D. :param kernel_size: size of the convolving kernel.

This class implements the CycleGAN model, for learning image-to-image translation without paired data. The model training requires '--dataset

Define different GAN objectives. The GANLoss class abstracts away the need to create the target label tensor that has the same size as the in

Define different GAN objectives. The GANLoss class abstracts away the need to create the target label tensor that has the same size as the in

Gaussian Smoothing 2D. :param sigma: sigma of the Gaussian. :param channels: number of channels in the output. :param kernel_size: a

Gaussian Smoothing 2D. :param sigma: sigma of the Gaussian. :param channels: number of channels in the output. :param kernel_size: a

A Python script for downloading CycleGAN or pix2pix datasets. Parameters: technique (str) -- One of: 'cyclegan' or 'pix2pix'. ver

Median Smoothing 2D. :param kernel_size: aperture linear size; must be odd and greater than 1. :param stride: stride of the convolution.

Median Smoothing 2D. :param kernel_size: aperture linear size; must be odd and greater than 1. :param stride: stride of the convolution.