```
tf.image.non_max_suppression_overlaps(
overlaps,
scores,
max_output_size,
overlap_threshold=0.5,
score_threshold=float('-inf'),
name=None
)
```

Defined in `tensorflow/python/ops/image_ops_impl.py`

.

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

Prunes away boxes that have high overlap with previously selected boxes.
N-by-n overlap values are supplied as square matrix.
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_overlaps(
overlaps, scores, max_output_size, iou_threshold)
selected_boxes = tf.gather(boxes, selected_indices)

#### Args:

: A 2-D float`overlaps`

`Tensor`

of shape`[num_boxes, num_boxes]`

.: A 1-D float`scores`

`Tensor`

of shape`[num_boxes]`

representing a single score corresponding to each box (each row of boxes).: A scalar integer`max_output_size`

`Tensor`

representing the maximum number of boxes to be selected by non max suppression.: A float representing the threshold for deciding whether boxes overlap too much with respect to the provided overlap values.`overlap_threshold`

: A float representing the threshold for deciding when to remove boxes based on score.`score_threshold`

: A name for the operation (optional).`name`

#### Returns:

: A 1-D integer`selected_indices`

`Tensor`

of shape`[M]`

representing the selected indices from the overlaps tensor, where`M <= max_output_size`

.