tf.math.argmax
Stay organized with collections
Save and categorize content based on your preferences.
Returns the index with the largest value across axes of a tensor.
tf.math.argmax(
input,
axis=None,
output_type=tf.dtypes.int64,
name=None
)
In case of identity returns the smallest index.
For example:
A = tf.constant([2, 20, 30, 3, 6])
tf.math.argmax(A) # A[2] is maximum in tensor A
<tf.Tensor: shape=(), dtype=int64, numpy=2>
B = tf.constant([[2, 20, 30, 3, 6], [3, 11, 16, 1, 8],
[14, 45, 23, 5, 27]])
tf.math.argmax(B, 0)
<tf.Tensor: shape=(5,), dtype=int64, numpy=array([2, 2, 0, 2, 2])>
tf.math.argmax(B, 1)
<tf.Tensor: shape=(3,), dtype=int64, numpy=array([2, 2, 1])>
C = tf.constant([0, 0, 0, 0])
tf.math.argmax(C) # Returns smallest index in case of ties
<tf.Tensor: shape=(), dtype=int64, numpy=0>
Args |
|---|
input
|
A Tensor.
|
axis
|
An integer, the axis to reduce across. Default to 0.
|
output_type
|
An optional output dtype (tf.int32 or tf.int64). Defaults
to tf.int64.
|
name
|
An optional name for the operation.
|
Returns |
|---|
A Tensor of type output_type.
|
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 2023-10-06 UTC.
[null,null,["Last updated 2023-10-06 UTC."],[],[],null,["# tf.math.argmax\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L268-L302) |\n\nReturns the index with the largest value across axes of a tensor.\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.argmax`](https://www.tensorflow.org/api_docs/python/tf/math/argmax)\n\n\u003cbr /\u003e\n\n tf.math.argmax(\n input,\n axis=None,\n output_type=../../tf/dtypes#int64,\n name=None\n )\n\nIn case of identity returns the smallest index.\n\n#### For example:\n\n A = tf.constant([2, 20, 30, 3, 6])\n tf.math.argmax(A) # A[2] is maximum in tensor A\n \u003ctf.Tensor: shape=(), dtype=int64, numpy=2\u003e\n B = tf.constant([[2, 20, 30, 3, 6], [3, 11, 16, 1, 8],\n [14, 45, 23, 5, 27]])\n tf.math.argmax(B, 0)\n \u003ctf.Tensor: shape=(5,), dtype=int64, numpy=array([2, 2, 0, 2, 2])\u003e\n tf.math.argmax(B, 1)\n \u003ctf.Tensor: shape=(3,), dtype=int64, numpy=array([2, 2, 1])\u003e\n C = tf.constant([0, 0, 0, 0])\n tf.math.argmax(C) # Returns smallest index in case of ties\n \u003ctf.Tensor: shape=(), dtype=int64, numpy=0\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|---------------|------------------------------------------------------------------------------------------------------------------------------------|\n| `input` | A `Tensor`. |\n| `axis` | An integer, the axis to reduce across. Default to 0. |\n| `output_type` | An optional output dtype ([`tf.int32`](../../tf#int32) or [`tf.int64`](../../tf#int64)). Defaults to [`tf.int64`](../../tf#int64). |\n| `name` | An optional name for the operation. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A `Tensor` of type `output_type`. ||\n\n\u003cbr /\u003e"]]
View source on GitHub