soft.crisp package

Subpackages

• soft.crisp.offline package
  • Submodules
  • soft.crisp.offline.supervised module
    • setup_from_config()
    • train()
  • Module contents

Submodules

soft.crisp.autoencode module

Implements a generic auto-encoder that is used in the Latent-Lockstep Method.

class soft.crisp.autoencode.AutoEncoder(in_features, latent_space_dim=4)

Bases: Module

A default auto-encoder; used for the latent-lockstep method.

forward(input_data: Tensor) → Tensor

Encode and decode the given input (input_data), and then return the decoded representation.

Parameters:

input_data – The input data to encode and decode.

Returns:

The decoded representation of the input data.

Module contents