tf.keras.layers.LeakyReLU
Stay organized with collections
Save and categorize content based on your preferences.
Leaky version of a Rectified Linear Unit.
Inherits From: Layer, Module
tf.keras.layers.LeakyReLU(
alpha=0.3, **kwargs
)
It allows a small gradient when the unit is not active:
f(x) = alpha * x if x < 0
f(x) = x if x >= 0
Usage:
layer = tf.keras.layers.LeakyReLU()
output = layer([-3.0, -1.0, 0.0, 2.0])
list(output.numpy())
[-0.9, -0.3, 0.0, 2.0]
layer = tf.keras.layers.LeakyReLU(alpha=0.1)
output = layer([-3.0, -1.0, 0.0, 2.0])
list(output.numpy())
[-0.3, -0.1, 0.0, 2.0]
|
|---|
Arbitrary. Use the keyword argument input_shape
(tuple of integers, does not include the batch axis)
when using this layer as the first layer in a model.
|
Output shape |
|---|
|
Same shape as the input.
|
Args |
|---|
alpha
|
Float >= 0. Negative slope coefficient. Default to 0.3.
|
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. Some content is licensed under the numpy license.
Last updated 2022-10-27 UTC.
[null,null,["Last updated 2022-10-27 UTC."],[],[],null,["# tf.keras.layers.LeakyReLU\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v2.7.0/keras/layers/advanced_activations.py#L32-L86) |\n\nLeaky version of a Rectified Linear Unit.\n\nInherits From: [`Layer`](../../../tf/keras/layers/Layer), [`Module`](../../../tf/Module)\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.LeakyReLU`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/LeakyReLU)\n\n\u003cbr /\u003e\n\n tf.keras.layers.LeakyReLU(\n alpha=0.3, **kwargs\n )\n\nIt allows a small gradient when the unit is not active: \n\n f(x) = alpha * x if x \u003c 0\n f(x) = x if x \u003e= 0\n\n#### Usage:\n\n layer = tf.keras.layers.LeakyReLU()\n output = layer([-3.0, -1.0, 0.0, 2.0])\n list(output.numpy())\n [-0.9, -0.3, 0.0, 2.0]\n layer = tf.keras.layers.LeakyReLU(alpha=0.1)\n output = layer([-3.0, -1.0, 0.0, 2.0])\n list(output.numpy())\n [-0.3, -0.1, 0.0, 2.0]\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Input shape ----------- ||\n|---|---|\n| Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the batch axis) when using this layer as the first layer in a model. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Output shape ------------ ||\n|---|---|\n| Same shape as the input. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|---------|----------------------------------------------------------|\n| `alpha` | Float \\\u003e= 0. Negative slope coefficient. Default to 0.3. |\n\n\u003cbr /\u003e"]]
View source on GitHub