nsl.lib.apply_feature_mask
Stay organized with collections
Save and categorize content based on your preferences.
Applies a feature mask on features
if the feature_mask
is not None
.
nsl.lib.apply_feature_mask(
features, feature_mask=None
)
Args |
features
|
A dense tensor representing features.
|
feature_mask
|
A dense tensor with values in [0, 1] and a broadcastable
shape to features . If not set, or set to None , the features are
returned unchanged.
|
Returns |
A dense tensor having the same shape as features .
|
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 2022-10-28 UTC.
[null,null,["Last updated 2022-10-28 UTC."],[],[],null,["# nsl.lib.apply_feature_mask\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/neural-structured-learning/blob/v1.4.0/neural_structured_learning/lib/utils.py#L456-L475) |\n\nApplies a feature mask on `features` if the `feature_mask` is not `None`. \n\n nsl.lib.apply_feature_mask(\n features, feature_mask=None\n )\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------------|------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `features` | A dense tensor representing features. |\n| `feature_mask` | A dense tensor with values in `[0, 1]` and a broadcastable shape to `features`. If not set, or set to `None`, the `features` are returned unchanged. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A dense tensor having the same shape as `features`. ||\n\n\u003cbr /\u003e"]]