Package org.tensorflow.op.image

Class NonMaxSuppression

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.image.NonMaxSuppression

All Implemented Interfaces:

Op

@Operator(group="image")
public final class NonMaxSuppression
extends PrimitiveOp

Greedily selects a subset of bounding boxes in descending order of score,

pruning away boxes that have high intersection-over-union (IOU) overlap with previously selected boxes. Bounding boxes with score less than `score_threshold` are removed. 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 and more generally 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 = tf.image.non_max_suppression_v2( boxes, scores, max_output_size, iou_threshold, score_threshold) selected_boxes = tf.gather(boxes, selected_indices)

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	NonMaxSuppression.Options	Optional attributes for NonMaxSuppression

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method	Description
static <T extends java.lang.Number> NonMaxSuppression	create(Scope scope, Operand<T> boxes, Operand<T> scores, Operand<java.lang.Integer> maxOutputSize, Operand<java.lang.Float> iouThreshold, Operand<java.lang.Float> scoreThreshold, NonMaxSuppression.Options... options)	Factory method to create a class to wrap a new NonMaxSuppression operation to the graph.
static NonMaxSuppression.Options	padToMaxOutputSize(java.lang.Boolean padToMaxOutputSize)
Output<java.lang.Integer>	selectedIndices()	A 1-D integer tensor of shape `[M]` representing the selected indices from the boxes tensor, where `M <= max_output_size`.
Output<java.lang.Integer>	validOutputs()	A 0-D integer tensor representing the number of valid elements in `selected_indices`, with the valid elements appearing first.

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Method Detail

create

public static <T extends java.lang.Number> NonMaxSuppression create(Scope scope,
                                                                    Operand<T> boxes,
                                                                    Operand<T> scores,
                                                                    Operand<java.lang.Integer> maxOutputSize,
                                                                    Operand<java.lang.Float> iouThreshold,
                                                                    Operand<java.lang.Float> scoreThreshold,
                                                                    NonMaxSuppression.Options... options)

Factory method to create a class to wrap a new NonMaxSuppression operation to the graph.

Parameters:

scope - current graph scope

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).

maxOutputSize - A scalar integer tensor representing the maximum number of boxes to be selected by non max suppression.

iouThreshold - A 0-D float tensor representing the threshold for deciding whether boxes overlap too much with respect to IOU.

scoreThreshold - A 0-D float tensor representing the threshold for deciding when to remove boxes based on score.

options - carries optional attributes values

Returns:

a new instance of NonMaxSuppression

padToMaxOutputSize

public static NonMaxSuppression.Options padToMaxOutputSize(java.lang.Boolean padToMaxOutputSize)

Parameters:

padToMaxOutputSize - If true, the output `selected_indices` is padded to be of length `max_output_size`. Defaults to false.

selectedIndices

public Output<java.lang.Integer> selectedIndices()

A 1-D integer tensor of shape `[M]` representing the selected indices from the boxes tensor, where `M <= max_output_size`.

validOutputs

public Output<java.lang.Integer> validOutputs()

A 0-D integer tensor representing the number of valid elements in `selected_indices`, with the valid elements appearing first.