tf.raw_ops.CombinedNonMaxSuppression

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

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.

boxes A Tensor of type float32. A 4-D float tensor of shape [batch_size, num_boxes, q, 4]. If q is 1 then same boxes are used for all classes otherwise, if q is equal to number of classes, class-specific boxes are used.
scores A Tensor of type 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).
max_output_size_per_class A Tensor of type int32. A scalar integer tensor representing the maximum number of boxes to be selected by non max suppression per class
max_total_size A Tensor of type int32. An int32 scalar representing the maximum number of boxes retained over all classes. Note that setting this value to a large number may result in OOM error depending on the system workload.
iou_threshold A Tensor of type float32. A 0-D float tensor representing the threshold for deciding whether boxes overlap too much with respect to IOU.
score_threshold A Tensor of type 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 max_size_per_class*num_classes, unless it exceeds max_total_size in 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).
nmsed_boxes A Tensor of type float32.
nmsed_scores A Tensor of type float32.
nmsed_classes A Tensor of type float32.
valid_detections A Tensor of type int32.