tfl.premade_lib.build_aggregation_layer

Creates an aggregation layer using the given calibrated lattice models.

tfl.premade_lib.build_aggregation_layer(
    aggregation_input_layer,
    model_config,
    calibrated_lattice_models,
    layer_output_range,
    submodel_index,
    dtype
)

aggregation_input_layer A list or a mapping from feature name to keras.Input, in the order or format expected by calibrated_lattice_models.
model_config Model configuration object describing model architecture. Should be one of the model configs in tfl.configs.
calibrated_lattice_models A list of calibrated lattice models of size model_config.middle_diemnsion, where each calbirated lattice model instance is constructed using the same model configuration object.
layer_output_range A tfl.premade_lib.LayerOutputRange enum.
submodel_index Corresponding index into submodels.
dtype dtype

A list of list of Tensors representing a calibration layer for submodels.