tf.image.non_max_suppression_with_scores
Stay organized with collections
Save and categorize content based on your preferences.
Greedily selects a subset of bounding boxes in descending order of score.
tf.image.non_max_suppression_with_scores(
boxes,
scores,
max_output_size,
iou_threshold=0.5,
score_threshold=float('-inf'),
soft_nms_sigma=0.0,
name=None
)
Prunes away boxes that have high intersection-over-union (IOU) overlap
with previously selected boxes. Bounding boxes are supplied as
[y1, x1, y2, x2]
, where (y1, x1)
and (y2, x2)
are the coordinates of any
diagonal pair of box corners and the coordinates can be provided as normalized
(i.e., lying in the interval [0, 1]
) or absolute. Note that this algorithm
is agnostic to where the origin is in the coordinate system. Note that this
algorithm is invariant to orthogonal transformations and translations
of the coordinate system; thus translating or reflections of the coordinate
system result in the same boxes being selected by the algorithm.
The output of this operation is a set of integers indexing into the input
collection of bounding boxes representing the selected boxes. The bounding
box coordinates corresponding to the selected indices can then be obtained
using the tf.gather
operation. For example:
selected_indices, selected_scores = tf.image.non_max_suppression_padded(
boxes, scores, max_output_size, iou_threshold=1.0, score_threshold=0.1,
soft_nms_sigma=0.5)
selected_boxes = tf.gather(boxes, selected_indices)
This function generalizes the tf.image.non_max_suppression
op by also
supporting a Soft-NMS (with Gaussian weighting) mode (c.f.
Bodla et al, https://arxiv.org/abs/1704.04503) where boxes reduce the score
of other overlapping boxes instead of directly causing them to be pruned.
Consequently, in contrast to tf.image.non_max_suppression
,
tf.image.non_max_suppression_with_scores
returns the new scores of each
input box in the second output, selected_scores
.
To enable this Soft-NMS mode, set the soft_nms_sigma
parameter to be
larger than 0. When soft_nms_sigma
equals 0, the behavior of
tf.image.non_max_suppression_with_scores
is identical to that of
tf.image.non_max_suppression
(except for the extra output) both in function
and in running time.
Note that when soft_nms_sigma
> 0, Soft-NMS is performed and iou_threshold
is ignored. iou_threshold
is only used for standard NMS.
Args |
boxes
|
A 2-D float Tensor of shape [num_boxes, 4] .
|
scores
|
A 1-D float Tensor of shape [num_boxes] representing a single
score corresponding to each box (each row of boxes).
|
max_output_size
|
A scalar integer Tensor representing the maximum number
of boxes to be selected by non-max suppression.
|
iou_threshold
|
A 0-D float tensor representing the threshold for deciding
whether boxes overlap too much with respect to IOU.
|
score_threshold
|
A 0-D float tensor representing the threshold for deciding
when to remove boxes based on score.
|
soft_nms_sigma
|
A 0-D float tensor representing the sigma parameter for Soft
NMS; see Bodla et al (c.f. https://arxiv.org/abs/1704.04503). When
soft_nms_sigma=0.0 (which is default), we fall back to standard (hard)
NMS.
|
name
|
A name for the operation (optional).
|
Returns |
selected_indices
|
A 1-D integer Tensor of shape [M] representing the
selected indices from the boxes tensor, where M <= max_output_size .
|
selected_scores
|
A 1-D float tensor of shape [M] representing the
corresponding scores for each selected box, where M <= max_output_size .
Scores only differ from corresponding input scores when using Soft NMS
(i.e. when soft_nms_sigma>0 )
|
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.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-04-26 UTC."],[],[],null,["# tf.image.non_max_suppression_with_scores\n\n\u003cbr /\u003e\n\n|------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.16.1/tensorflow/python/ops/image_ops_impl.py#L3836-L3923) |\n\nGreedily selects a subset of bounding boxes in descending order of score.\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.image.non_max_suppression_with_scores`](https://www.tensorflow.org/api_docs/python/tf/image/non_max_suppression_with_scores)\n\n\u003cbr /\u003e\n\n tf.image.non_max_suppression_with_scores(\n boxes,\n scores,\n max_output_size,\n iou_threshold=0.5,\n score_threshold=float('-inf'),\n soft_nms_sigma=0.0,\n name=None\n )\n\nPrunes away boxes that have high intersection-over-union (IOU) overlap\nwith previously selected boxes. Bounding boxes are supplied as\n`[y1, x1, y2, x2]`, where `(y1, x1)` and `(y2, x2)` are the coordinates of any\ndiagonal pair of box corners and the coordinates can be provided as normalized\n(i.e., lying in the interval `[0, 1]`) or absolute. Note that this algorithm\nis agnostic to where the origin is in the coordinate system. Note that this\nalgorithm is invariant to orthogonal transformations and translations\nof the coordinate system; thus translating or reflections of the coordinate\nsystem result in the same boxes being selected by the algorithm.\nThe output of this operation is a set of integers indexing into the input\ncollection of bounding boxes representing the selected boxes. The bounding\nbox coordinates corresponding to the selected indices can then be obtained\nusing the [`tf.gather`](../../tf/gather) operation. For example: \n\n selected_indices, selected_scores = tf.image.non_max_suppression_padded(\n boxes, scores, max_output_size, iou_threshold=1.0, score_threshold=0.1,\n soft_nms_sigma=0.5)\n selected_boxes = tf.gather(boxes, selected_indices)\n\nThis function generalizes the [`tf.image.non_max_suppression`](../../tf/image/non_max_suppression) op by also\nsupporting a Soft-NMS (with Gaussian weighting) mode (c.f.\nBodla et al, https://arxiv.org/abs/1704.04503) where boxes reduce the score\nof other overlapping boxes instead of directly causing them to be pruned.\nConsequently, in contrast to [`tf.image.non_max_suppression`](../../tf/image/non_max_suppression),\n[`tf.image.non_max_suppression_with_scores`](../../tf/image/non_max_suppression_with_scores) returns the new scores of each\ninput box in the second output, `selected_scores`.\n\nTo enable this Soft-NMS mode, set the `soft_nms_sigma` parameter to be\nlarger than 0. When `soft_nms_sigma` equals 0, the behavior of\n[`tf.image.non_max_suppression_with_scores`](../../tf/image/non_max_suppression_with_scores) is identical to that of\n[`tf.image.non_max_suppression`](../../tf/image/non_max_suppression) (except for the extra output) both in function\nand in running time.\n\nNote that when `soft_nms_sigma` \\\u003e 0, Soft-NMS is performed and `iou_threshold`\nis ignored. `iou_threshold` is only used for standard NMS.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `boxes` | A 2-D float `Tensor` of shape `[num_boxes, 4]`. |\n| `scores` | A 1-D float `Tensor` of shape `[num_boxes]` representing a single score corresponding to each box (each row of boxes). |\n| `max_output_size` | A scalar integer `Tensor` representing the maximum number of boxes to be selected by non-max suppression. |\n| `iou_threshold` | A 0-D float tensor representing the threshold for deciding whether boxes overlap too much with respect to IOU. |\n| `score_threshold` | A 0-D float tensor representing the threshold for deciding when to remove boxes based on score. |\n| `soft_nms_sigma` | A 0-D float tensor representing the sigma parameter for Soft NMS; see Bodla et al (c.f. https://arxiv.org/abs/1704.04503). When `soft_nms_sigma=0.0` (which is default), we fall back to standard (hard) NMS. |\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| `selected_indices` | A 1-D integer `Tensor` of shape `[M]` representing the selected indices from the boxes tensor, where `M \u003c= max_output_size`. |\n| `selected_scores` | A 1-D float tensor of shape `[M]` representing the corresponding scores for each selected box, where `M \u003c= max_output_size`. Scores only differ from corresponding input scores when using Soft NMS (i.e. when `soft_nms_sigma\u003e0`) |\n\n\u003cbr /\u003e"]]