DataDiscrete.get_ml_heads

DataDiscrete.get_ml_heads(head_layer_widths: List[int], last_core_layer_width: int, activation: torch.nn.Module, **kwargs) → Tuple[InHead, OutHead][source]

Returns two ML heads necessary for encoding and decoding the given data object.

Parameters:

  • head_layer_widths (List[int]) – List of integers where the length denotes number of layers and values the width of the layers in the head.

  • last_core_layer_width (int) – Dimensionality of autoencoder output to be decoded by this feature head.

  • activation (nn.Module) – Activation function to be used in this head.

  • kwargs – Additional keyword arguments passed to the head constructors.

Returns:

Tuple[nn.Module, nn.Module] – Tuple containing the input and output head.