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

tfl.lattice_layer.LatticeConstraints

View source on GitHub

Constraints for tfl.layers.Lattice layer.

tfl.lattice_layer.LatticeConstraints(
    lattice_sizes, monotonicities=None, unimodalities=None, edgeworth_trusts=None,
    trapezoid_trusts=None, monotonic_dominances=None, range_dominances=None,
    joint_monotonicities=None, output_min=None, output_max=None,
    num_projection_iterations=1, enforce_strict_monotonicity=True
)

Applies all constraints to the lattice weights. See tfl.layers.Lattice for more details.

Args:

  • lattice_sizes: Lattice sizes of Lattice layer to constraint.
  • monotonicities: Same meaning as corresponding parameter of Lattice.
  • unimodalities: Same meaning as corresponding parameter of Lattice.
  • edgeworth_trusts: Same meaning as corresponding parameter of Lattice.
  • trapezoid_trusts: Same meaning as corresponding parameter of Lattice.
  • monotonic_dominances: Same meaning as corresponding parameter of Lattice.
  • range_dominances: Same meaning as corresponding parameter of Lattice.
  • joint_monotonicities: Same meaning as corresponding parameter of Lattice.
  • output_min: Minimum possible output.
  • output_max: Maximum possible output.
  • num_projection_iterations: Same meaning as corresponding parameter of Lattice.
  • enforce_strict_monotonicity: Whether to use approximate projection to ensure that constratins are strictly satisfied.

Raises:

  • ValueError: If weights to project don't correspond to lattice_sizes.

Methods

__call__

View source

__call__(
    w
)

Applies constraints to w.

get_config

View source

get_config()

Standard Keras config for serialization.