tf.keras.layers.ActivityRegularization
Stay organized with collections
Save and categorize content based on your preferences.
Layer that applies an update to the cost function based input activity.
Inherits From: Layer
tf.keras.layers.ActivityRegularization(
l1=0.0, l2=0.0, **kwargs
)
Arguments |
|---|
l1
|
L1 regularization factor (positive float).
|
l2
|
L2 regularization factor (positive float).
|
Arbitrary. Use the keyword argument input_shape
(tuple of integers, does not include the samples axis)
when using this layer as the first layer in a model.
Output shape:
Same shape as input.
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 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.keras.layers.ActivityRegularization\n\n\u003cbr /\u003e\n\n|---------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------|\n| [TensorFlow 2 version](/api_docs/python/tf/keras/layers/ActivityRegularization) | [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/layers/core.py#L1085-L1114) |\n\nLayer that applies an update to the cost function based input activity.\n\nInherits From: [`Layer`](../../../tf/keras/layers/Layer)\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.keras.layers.ActivityRegularization`](/api_docs/python/tf/keras/layers/ActivityRegularization), \\`tf.compat.v2.keras.layers.ActivityRegularization\\`\n\n\u003cbr /\u003e\n\n tf.keras.layers.ActivityRegularization(\n l1=0.0, l2=0.0, **kwargs\n )\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Arguments --------- ||\n|------|--------------------------------------------|\n| `l1` | L1 regularization factor (positive float). |\n| `l2` | L2 regularization factor (positive float). |\n\n\u003cbr /\u003e\n\n#### Input shape:\n\nArbitrary. Use the keyword argument `input_shape`\n(tuple of integers, does not include the samples axis)\nwhen using this layer as the first layer in a model.\n\n#### Output shape:\n\nSame shape as input."]]
TensorFlow 2 version
View source on GitHub