tf.keras.activations.elu
Stay organized with collections
Save and categorize content based on your preferences.
Exponential linear unit.
tf.keras.activations.elu(
x, alpha=1.0
)
Arguments |
x
|
Input tensor.
|
alpha
|
A scalar, slope of negative section.
|
Returns |
The exponential linear activation: x if x > 0 and
alpha * (exp(x)-1) if x < 0 .
|
Reference:
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.activations.elu\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------|\n| [TensorFlow 1 version](/versions/r1.15/api_docs/python/tf/keras/activations/elu) | [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.1.0/tensorflow/python/keras/activations.py#L82-L98) |\n\nExponential linear unit.\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.activations.elu`](/api_docs/python/tf/keras/activations/elu)\n\n\u003cbr /\u003e\n\n tf.keras.activations.elu(\n x, alpha=1.0\n )\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Arguments --------- ||\n|---------|--------------------------------------|\n| `x` | Input tensor. |\n| `alpha` | A scalar, slope of negative section. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| The exponential linear activation: `x` if `x \u003e 0` and `alpha * (exp(x)-1)` if `x \u003c 0`. ||\n\n\u003cbr /\u003e\n\n#### Reference:\n\n- [Fast and Accurate Deep Network Learning by Exponential\n Linear Units (ELUs)](https://arxiv.org/abs/1511.07289)"]]