tf.contrib.nn.nth_element
Stay organized with collections
Save and categorize content based on your preferences.
Finds values of the n-th smallest value for the last dimension.
tf.contrib.nn.nth_element(
input, n, reverse=False, name=None
)
Note that n is zero-indexed.
If the input is a vector (rank-1), finds the entries which is the nth-smallest
value in the vector and outputs their values as scalar tensor.
For matrices (resp. higher rank input), computes the entries which is the
nth-smallest value in each row (resp. vector along the last dimension). Thus,
values.shape = input.shape[:-1]
Args |
|---|
input
|
1-D or higher Tensor with last dimension at least n+1.
|
n
|
A Tensor of type int32.
0-D. Position of sorted vector to select along the last dimension (along
each row for matrices). Valid range of n is [0, input.shape[:-1])
|
reverse
|
An optional bool. Defaults to False.
When set to True, find the nth-largest value in the vector and vice
versa.
|
name
|
A name for the operation (optional).
|
Returns |
|---|
A Tensor. Has the same type as input.
The n-th order statistic along each last dimensional slice.
|
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.contrib.nn.nth_element\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/ops/nn_ops.py#L4350-L4377) |\n\nFinds values of the `n`-th smallest value for the last dimension. \n\n tf.contrib.nn.nth_element(\n input, n, reverse=False, name=None\n )\n\nNote that n is zero-indexed.\n\nIf the input is a vector (rank-1), finds the entries which is the nth-smallest\nvalue in the vector and outputs their values as scalar tensor.\n\nFor matrices (resp. higher rank input), computes the entries which is the\nnth-smallest value in each row (resp. vector along the last dimension). Thus, \n\n values.shape = input.shape[:-1]\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-----------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `input` | 1-D or higher `Tensor` with last dimension at least `n+1`. |\n| `n` | A `Tensor` of type `int32`. 0-D. Position of sorted vector to select along the last dimension (along each row for matrices). Valid range of n is `[0, input.shape[:-1])` |\n| `reverse` | An optional `bool`. Defaults to `False`. When set to True, find the nth-largest value in the vector and vice versa. |\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 `input`. The `n`-th order statistic along each last dimensional slice. ||\n\n\u003cbr /\u003e"]]
View source on GitHub