tf.raw_ops.UnsortedSegmentMax
Stay organized with collections
Save and categorize content based on your preferences.
Computes the maximum along segments of a tensor.
tf.raw_ops.UnsortedSegmentMax(
data, segment_ids, num_segments, name=None
)
Read
the section on segmentation
for an explanation of segments.
This operator is similar to the unsorted segment sum operator found
(here).
Instead of computing the sum over segments, it computes the maximum such that:
\(output_i = \max_{j...} data[j...]\) where max is over tuples j... such
that segment_ids[j...] == i.
If the maximum is empty for a given segment ID i, it outputs the smallest
possible value for the specific numeric type,
output[i] = numeric_limits<T>::lowest().
If the given segment ID i is negative, then the corresponding value is
dropped, and will not be included in the result.
For example:
c = tf.constant([[1,2,3,4], [5,6,7,8], [4,3,2,1]])
tf.unsorted_segment_max(c, tf.constant([0, 1, 0]), num_segments=2)
# ==> [[ 4, 3, 3, 4],
# [5, 6, 7, 8]]
Args |
|---|
data
|
A Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, int64, bfloat16, uint16, half, uint32, uint64.
|
segment_ids
|
A Tensor. Must be one of the following types: int32, int64.
A tensor whose shape is a prefix of data.shape.
|
num_segments
|
A Tensor. Must be one of the following types: int32, int64.
|
name
|
A name for the operation (optional).
|
Returns |
|---|
A Tensor. Has the same type as data.
|
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.
Last updated 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.raw_ops.UnsortedSegmentMax\n\nComputes the maximum along segments of a tensor.\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.raw_ops.UnsortedSegmentMax`](/api_docs/python/tf/raw_ops/UnsortedSegmentMax)\n\n\u003cbr /\u003e\n\n tf.raw_ops.UnsortedSegmentMax(\n data, segment_ids, num_segments, name=None\n )\n\nRead\n[the section on segmentation](https://tensorflow.org/api_docs/python/tf/math#Segmentation)\nfor an explanation of segments.\n\nThis operator is similar to the unsorted segment sum operator found\n[(here)](../../../api_docs/python/math_ops#UnsortedSegmentSum).\nInstead of computing the sum over segments, it computes the maximum such that:\n\n\\\\(output_i = \\\\max_{j...} data\\[j...\\]\\\\) where max is over tuples `j...` such\nthat `segment_ids[j...] == i`.\n\nIf the maximum is empty for a given segment ID `i`, it outputs the smallest\npossible value for the specific numeric type,\n`output[i] = numeric_limits\u003cT\u003e::lowest()`.\n\nIf the given segment ID `i` is negative, then the corresponding value is\ndropped, and will not be included in the result. \n\n#### For example:\n\n c = tf.constant([[1,2,3,4], [5,6,7,8], [4,3,2,1]])\n tf.unsorted_segment_max(c, tf.constant([0, 1, 0]), num_segments=2)\n # ==\u003e [[ 4, 3, 3, 4],\n # [5, 6, 7, 8]]\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `data` | A `Tensor`. Must be one of the following types: `float32`, `float64`, `int32`, `uint8`, `int16`, `int8`, `int64`, `bfloat16`, `uint16`, `half`, `uint32`, `uint64`. |\n| `segment_ids` | A `Tensor`. Must be one of the following types: `int32`, `int64`. A tensor whose shape is a prefix of `data.shape`. |\n| `num_segments` | A `Tensor`. Must be one of the following types: `int32`, `int64`. |\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 `data`. ||\n\n\u003cbr /\u003e"]]
