tf.math.sign
Stay organized with collections
Save and categorize content based on your preferences.
Returns an element-wise indication of the sign of a number.
tf.math.sign(
x, name=None
)
Used in the notebooks
y = sign(x) = -1 if x < 0; 0 if x == 0; 1 if x > 0.
For complex numbers, y = sign(x) = x / |x| if x != 0, otherwise y = 0.
Example usage:
# real number
tf.math.sign([0., 2., -3.])
<tf.Tensor: shape=(3,), dtype=float32,
numpy=array([ 0., 1., -1.], dtype=float32)>
# complex number
tf.math.sign([1 + 1j, 0 + 0j])
<tf.Tensor: shape=(2,), dtype=complex128,
numpy=array([0.70710678+0.70710678j, 0. +0.j ])>
Args |
|---|
x
|
A Tensor. Must be one of the following types: bfloat16, half, float32,
float64, int32, int64, complex64, complex128.
|
name
|
A name for the operation (optional).
|
Returns |
|---|
|
A Tensor. Has the same type as x.
If x is a SparseTensor, returns SparseTensor(x.indices,
tf.math.sign(x.values, ...), x.dense_shape).
If x is a SparseTensor, returns
SparseTensor(x.indices, tf.math.sign(x.values, ...), x.dense_shape)
|
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.math.sign\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.16.1/tensorflow/python/ops/math_ops.py#L741-L785) |\n\nReturns an element-wise indication of the sign of a number.\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.sign`](https://www.tensorflow.org/api_docs/python/tf/math/sign)\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.sign`](https://www.tensorflow.org/api_docs/python/tf/math/sign)\n\n\u003cbr /\u003e\n\n tf.math.sign(\n x, name=None\n )\n\n### Used in the notebooks\n\n| Used in the tutorials |\n|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| - [Adversarial example using FGSM](https://www.tensorflow.org/tutorials/generative/adversarial_fgsm) - [Tutorial on Multi Armed Bandits in TF-Agents](https://www.tensorflow.org/agents/tutorials/bandits_tutorial) |\n\n`y = sign(x) = -1 if x \u003c 0; 0 if x == 0; 1 if x \u003e 0`.\n\nFor complex numbers, `y = sign(x) = x / |x| if x != 0, otherwise y = 0`.\n\n#### Example usage:\n\n # real number\n tf.math.sign([0., 2., -3.])\n \u003ctf.Tensor: shape=(3,), dtype=float32,\n numpy=array([ 0., 1., -1.], dtype=float32)\u003e\n\n # complex number\n tf.math.sign([1 + 1j, 0 + 0j])\n \u003ctf.Tensor: shape=(2,), dtype=complex128,\n numpy=array([0.70710678+0.70710678j, 0. +0.j ])\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|--------|----------------------------------------------------------------------------------------------------------------------|\n| `x` | A Tensor. Must be one of the following types: bfloat16, half, float32, float64, int32, int64, complex64, complex128. |\n| `name` | A name for the operation (optional). |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A Tensor. Has the same type as x. \u003cbr /\u003e If x is a SparseTensor, returns SparseTensor(x.indices, tf.math.sign(x.values, ...), x.dense_shape). If `x` is a `SparseTensor`, returns `SparseTensor(x.indices, tf.math.sign(x.values, ...), x.dense_shape)` ||\n\n\u003cbr /\u003e"]]
View source on GitHub