View source on GitHub
|
Mish activation function.
tfm.utils.activations.mish(
x
) -> tf.Tensor
Mish: A Self Regularized Non-Monotonic Activation Function https://arxiv.org/pdf/1908.08681.pdf
Mish(x) = x * tanh(ln(1+e^x))
Args | |
|---|---|
x
|
A Tensor representing preactivation values.
|
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 2024-02-02 UTC.