dice_ml.utils.sample_architecture package

Submodules

dice_ml.utils.sample_architecture.vae_model module

class dice_ml.utils.sample_architecture.vae_model.AutoEncoder(d, encoded_size)[source]

Bases: Module

decoder(z)[source]
encoder(x)[source]
forward(x)[source]

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.

normal_likelihood(x, mean, logvar, raxis=1)[source]
sample_latent_code(mean, logvar)[source]
training: bool
class dice_ml.utils.sample_architecture.vae_model.CF_VAE(d, encoded_size)[source]

Bases: Module

compute_elbo(x, c, pred_model)[source]
decoder(z)[source]
encoder(x)[source]
forward(x, c)[source]

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.

normal_likelihood(x, mean, logvar, raxis=1)[source]
sample_latent_code(mean, logvar)[source]
training: bool

Module contents