tfl.conditional_pwl_calibration.default_keypoint_input_parameters
Stay organized with collections
Save and categorize content based on your preferences.
Helper creating default keypoint_input_parameters.
tfl.conditional_pwl_calibration.default_keypoint_input_parameters(
num_keypoints: Optional[int] = None,
keypoints: Optional[Sequence[float]] = None,
units: int = 1
) -> Optional[tf.Tensor]
Primarily used for testing.
Args |
|---|
num_keypoints
|
number of keypoints. If provided, keypoints will be equally
spaced.
|
keypoints
|
sequence of increasing keypoints.
|
units
|
number of parallel calibrations on one input.
|
Returns |
|---|
A tensor with a shape of (1, units, input_param_size) or
(1, units, input_param_size).
|
Raises |
|---|
ValueError if parsing failed.
|
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.conditional_pwl_calibration.default_keypoint_input_parameters\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/conditional_pwl_calibration.py#L114-L147) |\n\nHelper creating default `keypoint_input_parameters`. \n\n tfl.conditional_pwl_calibration.default_keypoint_input_parameters(\n num_keypoints: Optional[int] = None,\n keypoints: Optional[Sequence[float]] = None,\n units: int = 1\n ) -\u003e Optional[tf.Tensor]\n\nPrimarily used for testing.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-----------------|---------------------------------------------------------------------|\n| `num_keypoints` | number of keypoints. If provided, keypoints will be equally spaced. |\n| `keypoints` | sequence of increasing keypoints. |\n| `units` | number of parallel calibrations on one input. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A tensor with a shape of `(1, units, input_param_size)` or `(1, units, input_param_size)`. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|---|---|\n| `ValueError` if parsing failed. ||\n\n\u003cbr /\u003e"]]
View source on GitHub