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

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

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

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

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

Parameters: width (int) : -- the width of input images height (int) : -- the height of input images n

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

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

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

Make models eval mode during test time

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

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

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)

Convert an Lab tensor image to a RGB numpy output Parameters: L (1-channel tensor array): L channel images (range: [-1, 1], torch

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.

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

Unpack input data from the dataloader and perform necessary pre-processing steps. Parameters: input: a dictionary that contains t

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

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_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

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. This will be 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

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

No optimization for test model.

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

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

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

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