FeatureConfig configuration class

[source]

FeatureConfig class

keras_rs.layers.FeatureConfig(
    name: str,
    table: keras_rs.src.layers.embedding.distributed_embedding_config.TableConfig,
    input_shape: Sequence[Optional[int]],
    output_shape: Sequence[Optional[int]],
)

Configuration for one embedding feature.

Configures one feature for keras_rs.layers.DistributedEmbedding. Each feature uses a table configured via keras_rs.layers.TableConfig and multiple features can share the same table.

Attributes

• name: The name of the feature. Must be defined.
• table: The table in which to look up this feature.
• input_shape: The input shape of the feature. The feature fed into the layer has to match the shape. Note that for ragged dimensions in the input, the dimension provided here presents the maximum value; anything larger will be truncated.
• output_shape: The output shape of the feature activation. What is returned by the embedding layer has to match this shape.