tfl.lattice_layer.LinearInitializer
Stay organized with collections
Save and categorize content based on your preferences.
Initializes a tfl.layers.Lattice as linear function.
tfl.lattice_layer.LinearInitializer(
lattice_sizes, monotonicities, output_min, output_max, unimodalities=None
)
- The linear function will have positive coefficients for monotonic dimensions
and 0 otherwise. If all dimensions are unconstrained, all coefficients will
be positive.
- Linear coefficients are set such that the minimum/maximum output of the
lattice matches the given output_min/output_max.
- Each monotonic dimension contributes with same weight regardless of number
of vertices per dimension.
- No dimension can be both monotonic and unimodal.
- Unimodal dimensions contribute with same weight as monotonic dimensions.
- Unimodal dimensions linearly decrease for first
(dim_size + 1) // 2
vertices and then linearly increase for following vertices.
Args |
|---|
lattice_sizes
|
Lattice sizes of tfl.layers.Lattice to initialize.
|
monotonicities
|
Monotonic dimensions for initialization. Does not need to
match monotonicities of tfl.layers.Lattice.
|
output_min
|
Minimum layer output after initialization.
|
output_max
|
Maximum layer output after initialization.
|
unimodalities
|
None or unimodal dimensions after initialization. Does not
need to match unimodalities of tfl.layers.Lattice.
|
Raises |
|---|
ValueError
|
If there is a mismatch between monotonicities and
lattice_sizes.
|
Methods
from_config
@classmethod
from_config(
config
)
Instantiates an initializer from a configuration dictionary.
Example:
initializer = RandomUniform(-1, 1)
config = initializer.get_config()
initializer = RandomUniform.from_config(config)
| Args |
|---|
config
|
A Python dictionary, the output of get_config().
|
| Returns |
|---|
An Initializer instance.
|
get_config
View source
get_config()
Standard Keras config for serialization.
__call__
View source
__call__(
shape, dtype=None, partition_info=None
)
Returns weights of tfl.layers.Lattice layer.
| Args |
|---|
shape
|
Must be: (prod(lattice_sizes), units).
|
dtype
|
Standard Keras initializer param.
|
partition_info
|
Standard Keras initializer param. Not used.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2024-08-02 UTC.
[null,null,["Last updated 2024-08-02 UTC."],[],[],null,["# tfl.lattice_layer.LinearInitializer\n\n\u003cbr /\u003e\n\n|---------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/lattice_layer.py#L653-L737) |\n\nInitializes a [`tfl.layers.Lattice`](../../tfl/layers/Lattice) as linear function. \n\n tfl.lattice_layer.LinearInitializer(\n lattice_sizes, monotonicities, output_min, output_max, unimodalities=None\n )\n\n- The linear function will have positive coefficients for monotonic dimensions and 0 otherwise. If all dimensions are unconstrained, all coefficients will be positive.\n- Linear coefficients are set such that the minimum/maximum output of the lattice matches the given output_min/output_max.\n- Each monotonic dimension contributes with same weight regardless of number of vertices per dimension.\n- No dimension can be both monotonic and unimodal.\n- Unimodal dimensions contribute with same weight as monotonic dimensions.\n- Unimodal dimensions linearly decrease for first `(dim_size + 1) // 2` vertices and then linearly increase for following vertices.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|\n| `lattice_sizes` | Lattice sizes of [`tfl.layers.Lattice`](../../tfl/layers/Lattice) to initialize. |\n| `monotonicities` | Monotonic dimensions for initialization. Does not need to match `monotonicities` of [`tfl.layers.Lattice`](../../tfl/layers/Lattice). |\n| `output_min` | Minimum layer output after initialization. |\n| `output_max` | Maximum layer output after initialization. |\n| `unimodalities` | None or unimodal dimensions after initialization. Does not need to match `unimodalities` of [`tfl.layers.Lattice`](../../tfl/layers/Lattice). |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|--------------|----------------------------------------------------------------------|\n| `ValueError` | If there is a mismatch between `monotonicities` and `lattice_sizes`. |\n\n\u003cbr /\u003e\n\nMethods\n-------\n\n### `from_config`\n\n @classmethod\n from_config(\n config\n )\n\nInstantiates an initializer from a configuration dictionary.\n\n#### Example:\n\n initializer = RandomUniform(-1, 1)\n config = initializer.get_config()\n initializer = RandomUniform.from_config(config)\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|----------|----------------------------------------------------|\n| `config` | A Python dictionary, the output of `get_config()`. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ||\n|---|---|\n| An `Initializer` instance. ||\n\n\u003cbr /\u003e\n\n### `get_config`\n\n[View source](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/lattice_layer.py#L728-L737) \n\n get_config()\n\nStandard Keras config for serialization.\n\n### `__call__`\n\n[View source](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/lattice_layer.py#L708-L726) \n\n __call__(\n shape, dtype=None, partition_info=None\n )\n\nReturns weights of [`tfl.layers.Lattice`](../../tfl/layers/Lattice) layer.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|------------------|---------------------------------------------|\n| `shape` | Must be: `(prod(lattice_sizes), units)`. |\n| `dtype` | Standard Keras initializer param. |\n| `partition_info` | Standard Keras initializer param. Not used. |\n\n\u003cbr /\u003e"]]
View source on GitHub