Class NonMaxSuppression.Inputs<T extends TNumber>

java.lang.Object

org.tensorflow.op.RawOpInputs<NonMaxSuppression<T>>

org.tensorflow.op.image.NonMaxSuppression.Inputs<T>

Enclosing class:

NonMaxSuppression<T extends TNumber>

public static class NonMaxSuppression.Inputs<T extends TNumber>
extends RawOpInputs<NonMaxSuppression<T>>

Field Summary

Fields

Modifier and Type	Field	Description
final Operand<T>	boxes	A 2-D float tensor of shape [num_boxes, 4].
final Operand<T>	iouThreshold	A 0-D float tensor representing the threshold for deciding whether boxes overlap too much with respect to IOU.
final Operand<TInt32>	maxOutputSize	A scalar integer tensor representing the maximum number of boxes to be selected by non max suppression.
final boolean	padToMaxOutputSize	If true, the output selected_indices is padded to be of length max_output_size.
final Operand<T>	scores	A 1-D float tensor of shape [num_boxes] representing a single score corresponding to each box (each row of boxes).
final Operand<T>	scoreThreshold	A 0-D float tensor representing the threshold for deciding when to remove boxes based on score.
final Operand<T>	softNmsSigma	A 0-D float tensor representing the sigma parameter for Soft NMS; see Bodla et al (c.f. https://arxiv.org/abs/1704.04503).
final DataType	T	The T attribute

Constructor Summary

Constructors

Constructor	Description
Inputs(GraphOperation op)

Method Summary

Methods inherited from class RawOpInputs

attributeMetadata, attributeNames, attributes, attributeValue, attributeValues, equals, getOutputs, hashCode, toString

Methods inherited from class Object

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

Field Details

boxes

public final Operand<T extends TNumber> boxes

A 2-D float tensor of shape [num_boxes, 4].

scores

public final Operand<T extends TNumber> scores

A 1-D float tensor of shape [num_boxes] representing a single score corresponding to each box (each row of boxes).

maxOutputSize

public final Operand<TInt32> maxOutputSize

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

iouThreshold

public final Operand<T extends TNumber> iouThreshold

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

scoreThreshold

public final Operand<T extends TNumber> scoreThreshold

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

softNmsSigma

public final Operand<T extends TNumber> softNmsSigma

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.

T

public final DataType T

The T attribute

padToMaxOutputSize

public final boolean padToMaxOutputSize

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

Constructor Details

Inputs

public Inputs(GraphOperation op)