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


View source on GitHub

Returns function which does lattice interpolation.

    lattice_sizes, monotonicities, output_min, output_max

Returned function matches lattice_layer.LinearInitializer with corresponding parameters.


  • lattice_sizes: list or tuple of integers which represents lattice sizes.
  • monotonicities: monotonicity constraints.
  • output_min: minimum output of linear function.
  • output_max: maximum output of linear function.


Function which takes d-dimension point and performs lattice interpolation assuming lattice weights are such that lattice represents linear function with given output_min and output_max. All monotonic dimesions of this linear function cotribute with same weight despite of numer of vertices per dimension. All non monotonic dimensions have weight 0.0.