FWIoU

$$FWIoU$$

FWIoU（Frequency Weighted Intersection over Union）:加权交并比

在MIoU上的基础上做的提升，对每一个类根据出现的频率为其设置权重

实现

gt_image = np.array([
    [0,1,2,4],
    [0,0,0,0],
    [0,0,0,0],
    [0,0,0,0]
])

pre_image = np.array([
    [0,1,2,4],
    [0,1,0,0],
    [0,1,0,0],
    [0,0,1,0]
])

def generate_matrix(gt_image, pre_image,num_class=8):
        mask = (gt_image >= 0) & (gt_image < num_class)#ground truth中所有正确(值在[0, classe_num])的像素label的mask
        
        label = num_class * gt_image[mask].astype('int') + pre_image[mask] 
        # np.bincount计算了从0到n**2-1这n**2个数中每个数出现的次数，返回值形状(n, n)
        count = np.bincount(label, minlength=num_class**2)
        confusion_matrix = count.reshape(num_class, num_class)#21 * 21(for pascal)
        return confusion_matrix
        
matrix =generate_matrix(gt_image,pre_image)

def Frequency_Weighted_Intersection_over_Union(confusion_matrix):
    freq = np.sum(confusion_matrix, axis=1) / np.sum(confusion_matrix)
    iu = np.diag(confusion_matrix) / (
                np.sum(confusion_matrix, axis=1) + np.sum(confusion_matrix, axis=0) -
                np.diag(confusion_matrix))

    FWIoU = (freq[freq > 0] * iu[freq > 0]).sum()
    return FWIoU
 
Frequency_Weighted_Intersection_over_Union(matrix)