Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings

tfl.premade_lib.build_linear_layer

View source on GitHub

Creates a tfl.layers.Linear layer initialized to be an average.

tfl.premade_lib.build_linear_layer(
    linear_input, feature_configs, model_config, weighted_average, submodel_index,
    dtype
)

Args:

  • linear_input: Input to the linear layer.
  • feature_configs: A list of tfl.configs.FeatureConfig instances that specify configurations for each feature.
  • model_config: Model configuration object describing model architecture. Should be one of the model configs in tfl.configs.
  • weighted_average: If the linear coefficients should be positive and sum up to one.
  • submodel_index: Corresponding index into submodels.
  • dtype: dtype

Returns:

A tfl.layers.Linear instance.