tfr.keras.utils.log2_inverse
Stay organized with collections
Save and categorize content based on your preferences.
Computes 1./log2(1+x) element-wise for each label.
tfr.keras.utils.log2_inverse(
rank: tfr.keras.model.TensorLike
) -> tf.Tensor
Can be used to define rank_discount_fn for tfr.keras.metrics.NDCGMetric.
Returns |
|---|
A Tensor that has each input element transformed as x to 1./log2(1+x).
|
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 2023-08-18 UTC.
[null,null,["Last updated 2023-08-18 UTC."],[],[],null,["# tfr.keras.utils.log2_inverse\n\n\u003cbr /\u003e\n\n|------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/ranking/blob/v0.5.3/tensorflow_ranking/python/keras/utils.py#L94-L107) |\n\nComputes `1./log2(1+x)` element-wise for each label. \n\n tfr.keras.utils.log2_inverse(\n rank: ../../../tfr/keras/model/TensorLike\n ) -\u003e tf.Tensor\n\nCan be used to define `rank_discount_fn` for [`tfr.keras.metrics.NDCGMetric`](../../../tfr/keras/metrics/NDCGMetric).\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|--------|-----------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `rank` | A `Tensor` or anything that can be converted to a tensor using [`tf.convert_to_tensor`](https://www.tensorflow.org/api_docs/python/tf/convert_to_tensor). |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A `Tensor` that has each input element transformed as `x` to `1./log2(1+x)`. ||\n\n\u003cbr /\u003e"]]
View source on GitHub