Greedily selects a subset of bounding boxes in descending order of score,
Compat aliases for migration
See Migration guide for more details.
tf.raw_ops.CombinedNonMaxSuppression( boxes, scores, max_output_size_per_class, max_total_size, iou_threshold, score_threshold, pad_per_class=False, clip_boxes=True, name=None )
This operation performs non_max_suppression on the inputs per batch, across all classes. 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. Also 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 the final boxes, scores and classes tensor returned after performing non_max_suppression.
float32. A 4-D float tensor of shape
[batch_size, num_boxes, q, 4]. If
qis 1 then same boxes are used for all classes otherwise, if
qis equal to number of classes, class-specific boxes are used.
float32. A 3-D float tensor of shape
[batch_size, num_boxes, num_classes]representing a single score corresponding to each box (each row of boxes).
int32. A scalar integer tensor representing the maximum number of boxes to be selected by non max suppression per class
int32. A scalar representing maximum number of boxes retained over all classes.
float32. A 0-D float tensor representing the threshold for deciding whether boxes overlap too much with respect to IOU.
float32. A 0-D float tensor representing the threshold for deciding when to remove boxes based on score.
pad_per_class: An optional
bool. Defaults to
False. If false, the output nmsed boxes, scores and classes are padded/clipped to
max_total_size. If true, the output nmsed boxes, scores and classes are padded to be of length
num_classes, unless it exceeds
max_total_sizein which case it is clipped to
max_total_size. Defaults to false.
clip_boxes: An optional
bool. Defaults to
True. If true, assume the box coordinates are between [0, 1] and clip the output boxes if they fall beyond [0, 1]. If false, do not do clipping and output the box coordinates as it is.
name: A name for the operation (optional).
A tuple of
Tensor objects (nmsed_boxes, nmsed_scores, nmsed_classes, valid_detections).