NMS算法(非极大值抑制)是目标检测算法中经典的后处理步骤，其本质是搜索局部最大值，抑制非极大值元素。主要利用目标检测框以及对应的置信度分数，设置一定的阈值来删除重叠较大的边界框。
其算法流程如下：

根据置信度得分进行排序
选择置信度最高的目标检测框添加到输出列表中，将其从检测框列表中删除
计算该检测框与剩余候选检测框的IOU
删除IOU大于阈值的检测框
重复上述4步，直至检测框列表为空

import numpy as npdef nms(dets, thresh):  # x1, y1, x2, y2, scorex1, y1, x2, y2, scores = dets[:, 0], dets[:, 1], dets[:, 2], dets[:, 3], dets[:, 4]areas = (x2 - x1 + 1) * (y2 - y1 + 1)  # 各个方框的面积order = scores.argsort()[::-1]  # 按置信度排序后的index， 作为候选集keep = []  # 保存筛选出来的方框的indexwhile order.size > 0:i = order[0]  # 当前置信度最大的方框keep.append(i)xx1 = np.maximum(x1[i], x1[order[1:]])xx2 = np.minimum(x2[i], x2[order[1:]])yy1 = np.maximum(y1[i], y1[order[1:]])yy2 = np.minimum(y2[i], y2[order[1:]])w = np.maximum(0.0, (xx2 - xx1 + 1))h = np.maximum(0.0, (yy2 - yy1 + 1))inter = w * h  # 当前置信度最大的框和其他所有框的相交面积overlap = inter / (areas[i] + areas[order[1:]] - inter)inds = np.where(overlap <= thresh)[0]  # 交并比小于thresh的仍然保留在候选集里， 大的过滤掉order = order[inds + 1]  # inds + 1对应原来order中overlap小于thresh的项return keepif __name__ == '__main__':detections = [[10, 20, 100, 100, 0.9],[20, 10, 110, 100, 0.88],[20, 20, 110, 110, 0.86],[40, 50, 200, 200, 0.95],[45, 52, 198, 202, 0.87]]detections = np.array(detections)keeps = nms(detections, 0.5)print(detections[keeps])