tfl.pwl_calibration_layer.PWLCalibrationConstraints
Stay organized with collections
Save and categorize content based on your preferences.
Monotonicity and bounds constraints for PWL calibration layer.
tfl.pwl_calibration_layer.PWLCalibrationConstraints(
monotonicity='none',
convexity='none',
lengths=None,
output_min=None,
output_max=None,
output_min_constraints=tfl.pwl_calibration_lib.BoundConstraintsType.NONE,
output_max_constraints=tfl.pwl_calibration_lib.BoundConstraintsType.NONE,
num_projection_iterations=8
)
Applies an approximate L2 projection to the weights of a PWLCalibration layer
such that the result satisfies the specified constraints.
Args |
|---|
monotonicity
|
Same meaning as corresponding parameter of PWLCalibration.
|
convexity
|
Same meaning as corresponding parameter of PWLCalibration.
|
lengths
|
Lengths of pieces of piecewise linear function. Needed only if
convexity is specified.
|
output_min
|
Minimum possible output of pwl function.
|
output_max
|
Maximum possible output of pwl function.
|
output_min_constraints
|
A tfl.pwl_calibration_lib.BoundConstraintsType
describing the constraints on the layer's minimum value.
|
output_max_constraints
|
A tfl.pwl_calibration_lib.BoundConstraintsType
describing the constraints on the layer's maximum value.
|
num_projection_iterations
|
Same meaning as corresponding parameter of
PWLCalibration.
|
Methods
from_config
@classmethod
from_config(
config
)
Instantiates a weight constraint from a configuration dictionary.
Example:
constraint = UnitNorm()
config = constraint.get_config()
constraint = UnitNorm.from_config(config)
| Args |
|---|
config
|
A Python dictionary, the output of get_config.
|
get_config
View source
get_config()
Standard Keras config for serialization.
__call__
View source
__call__(
w
)
Applies constraints to w.
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.pwl_calibration_layer.PWLCalibrationConstraints\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/pwl_calibration_layer.py#L688-L776) |\n\nMonotonicity and bounds constraints for PWL calibration layer. \n\n tfl.pwl_calibration_layer.PWLCalibrationConstraints(\n monotonicity='none',\n convexity='none',\n lengths=None,\n output_min=None,\n output_max=None,\n output_min_constraints=../../tfl/pwl_calibration_lib/BoundConstraintsType#NONE,\n output_max_constraints=../../tfl/pwl_calibration_lib/BoundConstraintsType#NONE,\n num_projection_iterations=8\n )\n\nApplies an approximate L2 projection to the weights of a PWLCalibration layer\nsuch that the result satisfies the specified constraints.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-----------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `monotonicity` | Same meaning as corresponding parameter of `PWLCalibration`. |\n| `convexity` | Same meaning as corresponding parameter of `PWLCalibration`. |\n| `lengths` | Lengths of pieces of piecewise linear function. Needed only if convexity is specified. |\n| `output_min` | Minimum possible output of pwl function. |\n| `output_max` | Maximum possible output of pwl function. |\n| `output_min_constraints` | A [`tfl.pwl_calibration_lib.BoundConstraintsType`](../../tfl/pwl_calibration_lib/BoundConstraintsType) describing the constraints on the layer's minimum value. |\n| `output_max_constraints` | A [`tfl.pwl_calibration_lib.BoundConstraintsType`](../../tfl/pwl_calibration_lib/BoundConstraintsType) describing the constraints on the layer's maximum value. |\n| `num_projection_iterations` | Same meaning as corresponding parameter of `PWLCalibration`. |\n\n\u003cbr /\u003e\n\nMethods\n-------\n\n### `from_config`\n\n @classmethod\n from_config(\n config\n )\n\nInstantiates a weight constraint from a configuration dictionary.\n\n#### Example:\n\n constraint = UnitNorm()\n config = constraint.get_config()\n constraint = UnitNorm.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| A [`tf.keras.constraints.Constraint`](https://www.tensorflow.org/api_docs/python/tf/keras/constraints/Constraint) 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/pwl_calibration_layer.py#L765-L776) \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/pwl_calibration_layer.py#L752-L763) \n\n __call__(\n w\n )\n\nApplies constraints to w."]]
View source on GitHub