![]() append ( float ( "inf" )) assert all ( low = low ) & ( matched_vals = num_valid_boxes # Will flag to - 1 all the padded boxes to avoid sampling them match_labels = item_assignment ( match_labels, mask_padded_boxes, - 1 ) return matches, match_labels def _ set_low_quality_matches ( self, match_labels, match_quality_matrix, num_valid_boxes ) : """ Produce additional matches for predictions that have only low-quality matches. insert ( 0, - float ( "inf" )) thresholds. The matcher returns (a) a vector of length N containing the index of the ground-truth element m in labels = All predictions with iou 0 thresholds. For example, if the elements are boxes, this matrix may contain box intersection-over-union overlap values. The matching is determined by the MxN match_quality_matrix, that characterizes how well each (ground-truth, prediction)-pair match each other. ![]() ![]() ![]() Each predicted element will have exactly zero or one matches each ground-truth element may be matched to zero or more predicted elements. optimize import linear_sum_assignment class Matcher : """This class assigns to each predicted " element " (e.g., a box) a ground-truth element. From typing import List import tensorflow as tf from kerod. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |