Function mindspore::dataset::ApplyNms

Function Documentation

std::vector<int> mindspore::dataset::ApplyNms(const std::vector<std::vector<float>> &all_boxes, std::vector<float> &all_scores, float thres, int max_boxes)

Apply Non-Maximum Suppression.

Example
/* Apply NMS on bboxes */
std::vector<std::vector<float>> all_boxes = {{1, 1, 2, 2}, {3, 3, 4, 4}, {5, 5, 6, 6}, {5, 5, 6, 6}};
std::vector<float> all_scores = {0.6, 0.5, 0.4, 0.9};
std::vector<int> keep = ApplyNms(all_boxes, all_scores, 0.5, 10);

Parameters

  • all_boxes – [in] All input boxes.

  • all_scores – [in] Score after all boxes are executed through the network.

  • thres – [in] Pre-value of IOU.

  • max_boxes – [in] Maximum value of output box.

Returns

Remaining bounding boxes.