vegans.utils.loading.architectures package

Submodules

vegans.utils.loading.architectures.celeba module

class vegans.utils.loading.architectures.celeba.MyAdversary(adv_in_dim, last_layer_activation)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

class vegans.utils.loading.architectures.celeba.MyDecoder(x_dim, dec_in_dim)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

class vegans.utils.loading.architectures.celeba.MyEncoder(enc_in_dim, z_dim)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

class vegans.utils.loading.architectures.celeba.MyGenerator(x_dim, gen_in_dim)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

vegans.utils.loading.architectures.celeba.load_celeba_adversary(x_dim, y_dim=None, adv_type='Critic')

Load some celeba architecture for the adversary.

Parameters

y_dim (integer, list, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for adversary.

Return type

torch.nn.Module

vegans.utils.loading.architectures.celeba.load_celeba_decoder(x_dim, z_dim, y_dim=None)

Load some mnist architecture for the decoder.

Parameters

• z_dim (integer, list) – Indicating the number of dimensions for the latent space.

• y_dim (integer, list, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for decoder.

Return type

torch.nn.Module

vegans.utils.loading.architectures.celeba.load_celeba_encoder(x_dim, z_dim, y_dim=None)

Load some celeba architecture for the encoder.

Parameters

• x_dim (integer, list) – Indicating the number of dimensions for the real data.

• z_dim (integer, list) – Indicating the number of dimensions for the latent space.

• y_dim (integer, list, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for encoder.

Return type

torch.nn.Module

vegans.utils.loading.architectures.celeba.load_celeba_generator(x_dim, z_dim, y_dim=None)

Load some celeba architecture for the generator.

Parameters

• z_dim (integer, list) – Indicating the number of dimensions for the latent space.

• y_dim (None, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for generator,.

Return type

torch.nn.Module

vegans.utils.loading.architectures.example module

class vegans.utils.loading.architectures.example.MyAdversary(adv_in_dim, first_layer, last_layer)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

class vegans.utils.loading.architectures.example.MyAutoEncoder(adv_in_dim, x_dim, first_layer)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

class vegans.utils.loading.architectures.example.MyDecoder(x_dim, dec_in_dim)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

class vegans.utils.loading.architectures.example.MyEncoder(enc_in_dim, z_dim, first_layer)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

class vegans.utils.loading.architectures.example.MyGenerator(gen_in_dim, x_dim)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

vegans.utils.loading.architectures.example.load_example_adversary(x_dim, y_dim=None, adv_type='Critic')

Load some example architecture for the adversary.

Parameters

• x_dim (integer, list) – Indicating the number of dimensions for the real data.

• y_dim (integer, list, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for adversary.

Return type

torch.nn.Module

vegans.utils.loading.architectures.example.load_example_autoencoder(x_dim, y_dim=None)

Load some example architecture for the auto-encoder.

Parameters

• x_dim (integer, list) – Indicating the number of dimensions for the real data.

• y_dim (integer, list, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for autoencoder.

Return type

torch.nn.Module

vegans.utils.loading.architectures.example.load_example_decoder(x_dim, z_dim, y_dim=None)

Load some example architecture for the decoder.

Parameters

• x_dim (integer, list) – Indicating the number of dimensions for the real data.

• z_dim (integer, list) – Indicating the number of dimensions for the latent space.

• y_dim (None, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for decoder.

Return type

torch.nn.Module

vegans.utils.loading.architectures.example.load_example_encoder(x_dim, z_dim, y_dim=None)

Load some example architecture for the encoder.

Parameters

• x_dim (integer, list) – Indicating the number of dimensions for the real data.

• z_dim (integer, list) – Indicating the number of dimensions for the latent space.

• y_dim (None, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for encoder.

Return type

torch.nn.Module

vegans.utils.loading.architectures.example.load_example_generator(x_dim, z_dim, y_dim=None)

Load some example architecture for the generator.

Parameters

• x_dim (integer, list) – Indicating the number of dimensions for the real data.

• z_dim (integer, list) – Indicating the number of dimensions for the latent space.

• y_dim (integer, list, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for generator,.

Return type

torch.nn.Module

vegans.utils.loading.architectures.mnist module

class vegans.utils.loading.architectures.mnist.MyAdversary(adv_in_dim, last_layer)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

class vegans.utils.loading.architectures.mnist.MyAutoEncoder(ae_in_dim)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

class vegans.utils.loading.architectures.mnist.MyDecoder(x_dim, dec_in_dim)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

class vegans.utils.loading.architectures.mnist.MyEncoder(enc_in_dim, z_dim)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

class vegans.utils.loading.architectures.mnist.MyGenerator(x_dim, gen_in_dim)

Bases: torch.nn.modules.module.Module

forward(x)

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.

training: bool

vegans.utils.loading.architectures.mnist.load_mnist_adversary(x_dim=(1, 32, 32), y_dim=None, adv_type='Critic')

Load some mnist architecture for the adversary.

Parameters

y_dim (integer, list, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for adversary.

Return type

torch.nn.Module

vegans.utils.loading.architectures.mnist.load_mnist_autoencoder(x_dim=(1, 32, 32), y_dim=None)

Load some mnist architecture for the auto-encoder.

Parameters

• x_dim (integer, list) – Indicating the number of dimensions for the real data.

• y_dim (integer, list, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for autoencoder.

Return type

torch.nn.Module

vegans.utils.loading.architectures.mnist.load_mnist_decoder(x_dim, z_dim, y_dim=None)

Load some mnist architecture for the decoder.

Parameters

• z_dim (integer, list) – Indicating the number of dimensions for the latent space.

• y_dim (integer, list, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for decoder.

Return type

torch.nn.Module

vegans.utils.loading.architectures.mnist.load_mnist_encoder(x_dim, z_dim, y_dim=None)

Load some mnist architecture for the encoder.

Parameters

• x_dim (integer, list) – Indicating the number of dimensions for the real data.

• z_dim (integer, list) – Indicating the number of dimensions for the latent space.

• y_dim (integer, list, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for encoder.

Return type

torch.nn.Module

vegans.utils.loading.architectures.mnist.load_mnist_generator(x_dim, z_dim, y_dim=None)

Load some mnist architecture for the generator.

Parameters

• z_dim (integer, list) – Indicating the number of dimensions for the latent space.

• y_dim (None, optional) – Indicating the number of dimensions for the labels.

Returns

Architectures for generator,.

Return type

torch.nn.Module

Module contents