tf.keras.activations.silu
Stay organized with collections
Save and categorize content based on your preferences.
Swish (or Silu) activation function.
tf.keras.activations.silu(
x
)
It is defined as: swish(x) = x * sigmoid(x).
The Swish (or Silu) activation function is a smooth,
non-monotonic function that is unbounded above and
bounded below.
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. Some content is licensed under the numpy license.
Last updated 2024-06-07 UTC.
[null,null,["Last updated 2024-06-07 UTC."],[],[],null,["# tf.keras.activations.silu\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v3.3.3/keras/src/activations/activations.py#L260-L277) |\n\nSwish (or Silu) activation function.\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.keras.activations.swish`](https://www.tensorflow.org/api_docs/python/tf/keras/activations/silu)\n\n\u003cbr /\u003e\n\n tf.keras.activations.silu(\n x\n )\n\nIt is defined as: `swish(x) = x * sigmoid(x)`.\n\nThe Swish (or Silu) activation function is a smooth,\nnon-monotonic function that is unbounded above and\nbounded below.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-----|---------------|\n| `x` | Input tensor. |\n\n\u003cbr /\u003e\n\n#### Reference:\n\n- [Ramachandran et al., 2017](https://arxiv.org/abs/1710.05941)"]]
View source on GitHub
