morpheus.models.dfencoder.ae_module.AEModule
- class AEModule(*args, **kwargs)[source]
Bases:
torch.nn.ModuleAuto Encoder Pytorch Module.
Methods
__call__(*args, **kwargs)Call self as a function. build(numeric_fts, binary_fts, categorical_fts)Constructs the autoencoder model. decode(x[, layers])Decodes the input using the decoder layers and computes the outputs. encode(x[, layers])Encodes the input using the encoder layers. forward(input)Passes the input through the model and returns the outputs. - build(numeric_fts, binary_fts, categorical_fts)[source]
Constructs the autoencoder model.
- Parameters
- numeric_ftsList[str]
The names of the numeric features.
- binary_ftsList[str]
The names of the binary features.
- categorical_ftsDict[str, Dict[str, List[str]]]
The dictionary mapping categorical feature names to dictionaries containing the categories of the feature.
- decode(x, layers=None)[source]
Decodes the input using the decoder layers and computes the outputs.
- Parameters
- xtorch.Tensor
The encoded input tensor to decode.
- layersint, optional
The number of layers to use for decoding. Defaults to None, will use all decoder layers.
- Returns
- tuple of Union[torch.Tensor, List[torch.Tensor]]
A tuple containing the numeric (Tensor), binary (Tensor), and categorical outputs (List[torch.Tensor]) of the model.
- encode(x, layers=None)[source]
Encodes the input using the encoder layers.
- Parameters
- xtorch.Tensor
The input tensor to encode.
- layersint, optional
The number of layers to use for encoding. Defaults to None, will use all encoder layers.
- Returns
- torch.Tensor
The encoded output tensor.
- forward(input)[source]
Passes the input through the model and returns the outputs.
- Parameters
- inputtorch.Tensor
The input tensor.
- Returns
- tuple of Union[torch.Tensor, List[torch.Tensor]]
A tuple containing the numeric (Tensor), binary (Tensor), and categorical outputs (List[torch.Tensor]) of the model.