tfl.pwl_calibration_lib.compute_interpolation_weights
Stay organized with collections
Save and categorize content based on your preferences.
Computes weights for PWL calibration.
tfl.pwl_calibration_lib.compute_interpolation_weights(
inputs, keypoints, lengths
)
Args |
|---|
inputs
|
Tensor of shape: (batch_size, 1), (batch_size, units, 1) or
(batch_size, 1, 1). For multi-unit calibration, broadcasting will be used
if needed.
|
keypoints
|
Tensor of shape (num_keypoints-1) or (units, num_keypoints-1)
which represents left keypoint of pieces of piecewise linear function
along X axis.
|
lengths
|
Tensor of shape (num_keypoints-1) or (units, num_keypoints-1)
which represents lengths of pieces of piecewise linear function along X
axis.
|
Returns |
|---|
Interpolation weights tensor of shape: (batch_size, num_keypoints) or
(batch_size, units, num_keypoints).
|
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_lib.compute_interpolation_weights\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_lib.py#L95-L126) |\n\nComputes weights for PWL calibration. \n\n tfl.pwl_calibration_lib.compute_interpolation_weights(\n inputs, keypoints, lengths\n )\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-------------|--------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `inputs` | Tensor of shape: `(batch_size, 1)`, `(batch_size, units, 1)` or `(batch_size, 1, 1)`. For multi-unit calibration, broadcasting will be used if needed. |\n| `keypoints` | Tensor of shape `(num_keypoints-1)` or `(units, num_keypoints-1)` which represents left keypoint of pieces of piecewise linear function along X axis. |\n| `lengths` | Tensor of shape `(num_keypoints-1)` or `(units, num_keypoints-1)` which represents lengths of pieces of piecewise linear function along X axis. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| Interpolation weights tensor of shape: `(batch_size, num_keypoints)` or `(batch_size, units, num_keypoints)`. ||\n\n\u003cbr /\u003e"]]
View source on GitHub
