steganogan.encoders module

class steganogan.encoders.BasicEncoder(data_depth, hidden_size)

Bases: torch.nn.modules.module.Module

The BasicEncoder module takes an cover image and a data tensor and combines them into a steganographic image.

Input: (N, 3, H, W), (N, D, H, W) Output: (N, 3, H, W)

add_image = False

forward(image, data)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

upgrade_legacy()

Transform legacy pretrained models to make them usable with new code versions.

class steganogan.encoders.DenseEncoder(data_depth, hidden_size)

Bases: steganogan.encoders.BasicEncoder

The DenseEncoder module takes an cover image and a data tensor and combines them into a steganographic image.

Input: (N, 3, H, W), (N, D, H, W) Output: (N, 3, H, W)

add_image = True

class steganogan.encoders.ResidualEncoder(data_depth, hidden_size)

Bases: steganogan.encoders.BasicEncoder

The ResidualEncoder module takes an cover image and a data tensor and combines them into a steganographic image.

Input: (N, 3, H, W), (N, D, H, W) Output: (N, 3, H, W)

add_image = True