create empty directories if they don't exist Parameters: paths (str list) -- a list of directory paths

Add new dataset-specific options, and rewrite default values for existing options. Parameters: parser -- original option

Add new model-specific options, and rewrite default values for existing options. Parameters: parser -- original option p

Add new dataset-specific options, and rewrite default values for existing options. Parameters: parser -- original option

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

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

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

White-box attack against blur pre-processing.

White-box attack against blur pre-processing.

White-box attack against blur pre-processing.

EoT adaptation to the blur transformation.

EoT adaptation to the blur transformation.

EoT adaptation to the blur transformation.

Spread-spectrum attack against blur defenses (gray-box scenario).

Spread-spectrum attack against blur defenses (gray-box scenario).

Spread-spectrum attack against blur defenses (gray-box scenario).

Iterative Class Conditional Attack

Iterative Class Conditional Attack

Iterative Class Conditional Attack

Joint Class Conditional Attack

Joint Class Conditional Attack

Joint Class Conditional Attack

Print the mean, min, max, median, std, and size of a numpy array Parameters: val (bool) -- if print the values of the numpy array

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

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

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

Converts a Tensor array into a numpy image array. Parameters: input_image (tensor) -- the input image tensor array imtype (type)

Translate images using StarGAN trained on a single dataset. No attack.

Translate images using StarGAN trained on a single dataset.

Translate images using StarGAN trained on a single dataset. No attack.

Vanilla or blur attacks.

Vanilla or blur attacks.

Class conditional transfer

Class conditional transfer

Feature-level attacks

Feature-level attacks

Universal Attack by Huang Hao

Universal Attack by Huang Hao

Universal Attack by Huang Hao

Universal Attack by Huang Hao

Universal Attack by Huang Hao

Universal Attack by Huang Hao

Universal Attack by Huang Hao

Vanilla Training of StarGAN within a single dataset.

Train StarGAN within a single dataset.

Vanilla Training of StarGAN within a single dataset.

G+D Adversarial Training for StarGAN with both Discriminator and Generator, within a single dataset.

Adversarial Training for StarGAN only for Generator, within a single dataset.

Adversarial Training for StarGAN only for Generator, within a single dataset.

Vanilla Attack.