tf.keras.ops.softplus
Stay organized with collections
Save and categorize content based on your preferences.
Softplus activation function.
tf.keras.ops.softplus(
x
)
It is defined as f(x) = log(exp(x) + 1), where log is the natural
logarithm and exp is the exponential function.
Returns |
|---|
A tensor with the same shape as x.
|
Example:
x = keras.ops.convert_to_tensor([-0.555, 0.0, 0.555])
keras.ops.softplus(x)
array([0.45366603, 0.6931472, 1.008666], dtype=float32)
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.ops.softplus\n\n\u003cbr /\u003e\n\n|--------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v3.3.3/keras/src/ops/nn.py#L120-L142) |\n\nSoftplus activation function.\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.keras.ops.nn.softplus`](https://www.tensorflow.org/api_docs/python/tf/keras/ops/softplus)\n\n\u003cbr /\u003e\n\n tf.keras.ops.softplus(\n x\n )\n\nIt is defined as `f(x) = log(exp(x) + 1)`, where `log` is the natural\nlogarithm and `exp` is the exponential function.\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\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A tensor with the same shape as `x`. ||\n\n\u003cbr /\u003e\n\n#### Example:\n\n x = keras.ops.convert_to_tensor([-0.555, 0.0, 0.555])\n keras.ops.softplus(x)\n array([0.45366603, 0.6931472, 1.008666], dtype=float32)"]]
View source on GitHub