Greedily selects a subset of bounding boxes in descending order of score,.
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.
[num_boxes]representing a single score corresponding to each box (each row of boxes).
soft_nms_sigma=0.0(which is default), we fall back to standard (hard) NMS.
Optional attributes (see
selected_indicesis padded to be of length
max_output_size. Defaults to false.
Outputselected_indices: A 1-D integer tensor of shape
[M]representing the selected indices from the boxes tensor, where
M <= max_output_size.
Outputselected_scores: A 1-D float tensor of shape
[M]representing the corresponding scores for each selected box, where
M <= max_output_size. Scores only differ from corresponding input scores when using Soft NMS (i.e. when
Outputvalid_outputs: A 0-D integer tensor representing the number of valid elements in
selected_indices, with the valid elements appearing first.
|Constructors and Destructors|
|Public static functions|
Optional attribute setters for NonMaxSuppressionV5.
NonMaxSuppressionV5( const ::tensorflow::Scope & scope, ::tensorflow::Input boxes, ::tensorflow::Input scores, ::tensorflow::Input max_output_size, ::tensorflow::Input iou_threshold, ::tensorflow::Input score_threshold, ::tensorflow::Input soft_nms_sigma )
NonMaxSuppressionV5( const ::tensorflow::Scope & scope, ::tensorflow::Input boxes, ::tensorflow::Input scores, ::tensorflow::Input max_output_size, ::tensorflow::Input iou_threshold, ::tensorflow::Input score_threshold, ::tensorflow::Input soft_nms_sigma, const NonMaxSuppressionV5::Attrs & attrs )
Attrs PadToMaxOutputSize( bool x )
© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.