# Module: tfl.kronecker_factored_lattice_lib

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/kronecker_factored_lattice_lib.py) |

Algorithm implementations required for Kronecker-Factored Lattice layer.

## Functions

[`assert_constraints(...)`](https://www.tensorflow.org/lattice/api_docs/python/tfl/kronecker_factored_lattice_lib/assert_constraints): Asserts that weights satisfy constraints.

[`bias_initializer(...)`](https://www.tensorflow.org/lattice/api_docs/python/tfl/kronecker_factored_lattice_lib/bias_initializer): Initializes bias depending on output_min and output_max.

[`custom_reduce_prod(...)`](https://www.tensorflow.org/lattice/api_docs/python/tfl/kronecker_factored_lattice_lib/custom_reduce_prod): tf.reduce_prod(t, axis) with faster custom gradient.

[`default_init_params(...)`](https://www.tensorflow.org/lattice/api_docs/python/tfl/kronecker_factored_lattice_lib/default_init_params): Returns default initialization bounds depending on layer output bounds.

[`evaluate_with_hypercube_interpolation(...)`](https://www.tensorflow.org/lattice/api_docs/python/tfl/kronecker_factored_lattice_lib/evaluate_with_hypercube_interpolation): Evaluates a Kronecker-Factored Lattice using hypercube interpolation.

[`finalize_scale_constraints(...)`](https://www.tensorflow.org/lattice/api_docs/python/tfl/kronecker_factored_lattice_lib/finalize_scale_constraints): Clips scale to strictly satisfy all constraints.

[`finalize_weight_constraints(...)`](https://www.tensorflow.org/lattice/api_docs/python/tfl/kronecker_factored_lattice_lib/finalize_weight_constraints): Approximately projects weights to strictly satisfy all constraints.

[`kfl_random_monotonic_initializer(...)`](https://www.tensorflow.org/lattice/api_docs/python/tfl/kronecker_factored_lattice_lib/kfl_random_monotonic_initializer): Returns a uniformly random sampled monotonic weight tensor.

[`scale_initializer(...)`](https://www.tensorflow.org/lattice/api_docs/python/tfl/kronecker_factored_lattice_lib/scale_initializer): Initializes scale depending on output_min and output_max.

[`verify_hyperparameters(...)`](https://www.tensorflow.org/lattice/api_docs/python/tfl/kronecker_factored_lattice_lib/verify_hyperparameters): Verifies that all given hyperparameters are consistent.

<br />

<br />

<br />

| ## Other Members ||
|---|---|
| absolute_import | Instance of `__future__._Feature` |
| division | Instance of `__future__._Feature` |
| print_function | Instance of `__future__._Feature` |

<br />