T
- data type for selectedScores()
output@Operator public final class NonMaxSuppressionV5<T extends Number> extends PrimitiveOp
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) This op also supports 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. To enable this Soft-NMS mode, set the `soft_nms_sigma` parameter to be larger than 0.
Modifier and Type | Class and Description |
---|---|
static class |
NonMaxSuppressionV5.Options
Optional attributes for
NonMaxSuppressionV5 |
operation
Modifier and Type | Method and Description |
---|---|
static <T extends Number> |
create(Scope scope,
Operand<T> boxes,
Operand<T> scores,
Operand<Integer> maxOutputSize,
Operand<T> iouThreshold,
Operand<T> scoreThreshold,
Operand<T> softNmsSigma,
NonMaxSuppressionV5.Options... options)
Factory method to create a class wrapping a new NonMaxSuppressionV5 operation.
|
static NonMaxSuppressionV5.Options |
padToMaxOutputSize(Boolean padToMaxOutputSize) |
Output<Integer> |
selectedIndices()
A 1-D integer tensor of shape `[M]` representing the selected
indices from the boxes tensor, where `M <= max_output_size`.
|
Output<T> |
selectedScores()
A 1-D float tensor of shape `[M]` representing the corresponding
scores for each selected box, where `M <= max_output_size`.
|
Output<Integer> |
validOutputs()
A 0-D integer tensor representing the number of valid elements in
`selected_indices`, with the valid elements appearing first.
|
equals, hashCode, op, toString
public static <T extends Number> NonMaxSuppressionV5<T> create(Scope scope, Operand<T> boxes, Operand<T> scores, Operand<Integer> maxOutputSize, Operand<T> iouThreshold, Operand<T> scoreThreshold, Operand<T> softNmsSigma, NonMaxSuppressionV5.Options... options)
scope
- current scopeboxes
- 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.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.options
- carries optional attributes valuespublic static NonMaxSuppressionV5.Options padToMaxOutputSize(Boolean padToMaxOutputSize)
padToMaxOutputSize
- If true, the output `selected_indices` is padded to be of length
`max_output_size`. Defaults to false.public Output<Integer> selectedIndices()
public Output<T> selectedScores()
Copyright © 2022. All rights reserved.