使用numpy广播的方法,在python程序中并不建议使用for语句,python中的for语句耗时较多,如果使用numpy广播的思想将会提速不少。
代码:
def calc_IoU(bBox1,bBox2): if not isinstance(bBox1,np.ndarray): bBox1 = np.array(bBox1) if not isinstance(bBox2,np.ndarray): bBox2 = np.array(bBox2) xmin1,ymin1,xmax1,ymax1,= np.split(bBox1,4,axis=-1) xmin2,ymin2,xmax2,ymax2,= np.split(bBox2,axis=-1) area1 = (xmax1 - xmin1) * (ymax1 - ymin1) area2 = (xmax2 - xmin2) * (ymax2 - ymin2) ymin = np.maximum(ymin1,np.squeeze(ymin2,axis=-1)) xmin = np.maximum(xmin1,np.squeeze(xmin2,axis=-1)) ymax = np.minimum(ymax1,np.squeeze(ymax2,axis=-1)) xmax = np.minimum(xmax1,np.squeeze(xmax2,axis=-1)) h = np.maximum(ymax - ymin,0) w = np.maximum(xmax - xmin,0) intersect = h * w union = area1 + np.squeeze(area2,axis=-1) - intersect return intersect / union
程序中输入为多个矩形[xmin,ymin,xmax,ymax]格式的数组或者list,输出为numpy格式,例:输入的shape为(3, 4)、(5,4)则输出为(3, 5)各个位置为Boxes间相互的IoU值。后面会卡一个IoU的阈值,然后就可以将满足条件的索引取出。如:
def delete_bBox(bBox1,bBox2,roi_bBox1,roi_bBox2,class1,class2,idx1,idx2,IoU_value): idx = np.where(IoU_value > 0.4) left_idx = idx[0] right_idx = idx[1] left = roi_bBox1[left_idx] right = roi_bBox2[right_idx] xmin1,= np.split(left,= np.split(right,axis=-1) left_area = (xmax1 - xmin1) * (ymax1 - ymin1) right_area = (xmax2 - xmin2) * (ymax2 - ymin2) left_idx = left_idx[np.squeeze(left_area < right_area,axis=-1)]#小的被删 right_idx = right_idx[np.squeeze(left_area > right_area,axis=-1)] bBox1 = np.delete(bBox1,idx1[left_idx],0) class1 = np.delete(class1,idx1[left_idx]) bBox2 = np.delete(bBox2,idx2[right_idx],0) class2 = np.delete(class2,idx2[right_idx]) return bBox1,class2
IoU计算原理:
ymin = np.maximum(ymin1,axis=-1)) xmin = np.maximum(xmin1,axis=-1)) ymax = np.minimum(ymax1,axis=-1)) xmax = np.minimum(xmax1,axis=-1)) h = np.maximum(ymax - ymin,0) w = np.maximum(xmax - xmin,0) intersect = h * w
计算矩形间min的最大值,max的最小值,如果ymax-ymin值大于0则如左图所示,如果小于0则如右图所示
以上这篇python不使用for计算两组、多个矩形两两间的IoU方式就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持我们。