tf.keras.ops.log_softmax
Stay organized with collections
Save and categorize content based on your preferences.
Log-softmax activation function.
tf.keras.ops.log_softmax(
x, axis=-1
)
It is defined as:
f(x) = x - max(x) - log(sum(exp(x - max(x))))
Args |
|---|
x
|
Input tensor.
|
axis
|
Integer, axis along which the log-softmax is applied.
Defaults to -1.
|
Returns |
|---|
A tensor with the same shape as x.
|
Example:
x = np.array([-1., 0., 1.])
x_log_softmax = keras.ops.log_softmax(x)
print(x_log_softmax)
array([-2.40760596, -1.40760596, -0.40760596], shape=(3,), dtype=float64)
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.log_softmax\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#L589-L639) |\n\nLog-softmax activation function.\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.keras.ops.nn.log_softmax`](https://www.tensorflow.org/api_docs/python/tf/keras/ops/log_softmax)\n\n\u003cbr /\u003e\n\n tf.keras.ops.log_softmax(\n x, axis=-1\n )\n\n#### It is defined as:\n\n`f(x) = x - max(x) - log(sum(exp(x - max(x))))`\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|--------|-------------------------------------------------------------------------|\n| `x` | Input tensor. |\n| `axis` | Integer, axis along which the log-softmax is applied. Defaults to `-1`. |\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 = np.array([-1., 0., 1.])\n x_log_softmax = keras.ops.log_softmax(x)\n print(x_log_softmax)\n array([-2.40760596, -1.40760596, -0.40760596], shape=(3,), dtype=float64)"]]
View source on GitHub