tf.compat.v1.nn.silu
Stay organized with collections
Save and categorize content based on your preferences.
Computes the SiLU or Swish activation function: x * sigmoid(beta * x).
tf.compat.v1.nn.silu(
features, beta=1.0
)
beta : Hyperparameter for Swish activation function. Default value 1.0.
The SiLU activation function was introduced in "Gaussian Error Linear Units
(GELUs)" Hendrycks et al. 2016 and
"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in
Reinforcement Learning"
Elfwing et al. 2017 and was independently
discovered (and called swish) in "Searching for Activation Functions"
Ramachandran et al. 2017
Args |
|---|
features
|
A Tensor representing preactivation values.
|
beta
|
A 'Tensor' representing value of beta hyperparameter.
|
Returns |
|---|
|
The activation value.
|
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 2024-04-26 UTC.
[null,null,["Last updated 2024-04-26 UTC."],[],[],null,["# tf.compat.v1.nn.silu\n\n\u003cbr /\u003e\n\n|---------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.16.1/tensorflow/python/ops/nn_impl.py#L430-L483) |\n\nComputes the SiLU or Swish activation function: `x * sigmoid(beta * x)`.\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.nn.swish`](https://www.tensorflow.org/api_docs/python/tf/compat/v1/nn/silu)\n\n\u003cbr /\u003e\n\n tf.compat.v1.nn.silu(\n features, beta=1.0\n )\n\nbeta : Hyperparameter for Swish activation function. Default value 1.0.\n\nThe SiLU activation function was introduced in \"Gaussian Error Linear Units\n(GELUs)\" [Hendrycks et al. 2016](https://arxiv.org/abs/1606.08415) and\n\"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in\nReinforcement Learning\"\n[Elfwing et al. 2017](https://arxiv.org/abs/1702.03118) and was independently\ndiscovered (and called swish) in \"Searching for Activation Functions\"\n[Ramachandran et al. 2017](https://arxiv.org/abs/1710.05941)\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|------------|-------------------------------------------------------|\n| `features` | A `Tensor` representing preactivation values. |\n| `beta` | A 'Tensor' representing value of beta hyperparameter. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| The activation value. ||\n\n\u003cbr /\u003e"]]
View source on GitHub