tf.image.non_max_suppression_overlaps | TensorFlow v2.16.1 (original) (raw)

tf.image.non_max_suppression_overlaps

Stay organized with collections Save and categorize content based on your preferences.

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

View aliases

Compat aliases for migration

tf.compat.v1.image.non_max_suppression_overlaps

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

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
overlaps	A 2-D float Tensor of shape [num_boxes, num_boxes]representing the n-by-n box overlap values.
scores	A 1-D float Tensor of shape [num_boxes] representing a single score corresponding to each box (each row of boxes).
max_output_size	A scalar integer Tensor representing the maximum number of boxes to be selected by non-max suppression.
overlap_threshold	A 0-D float tensor representing the threshold for deciding whether boxes overlap too much with respect to the provided overlap values.
score_threshold	A 0-D float tensor representing the threshold for deciding when to remove boxes based on score.
name	A name for the operation (optional).

Returns
selected_indices	A 1-D integer Tensor of shape [M] representing the selected indices from the overlaps tensor, where M <= max_output_size.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-04-26 UTC.