如何测量两个图像的骰子系数

Question

我有两个相同的 RGB 图像并尝试找到骰子系数。我希望结果是 1.0，但实际上是 0.0039。

我做错了什么？？

from skimage.io import imread

def dice_coef(y_true, y_pred):
    smooth = 1
    y_true_f = y_true.flatten()
    y_pred_f = y_pred.flatten()
    intersection = (sum(y_true_f * y_pred_f))
    return (2. * intersection + smooth) / (sum(y_true_f) + sum(y_pred_f) + smooth)

im=imread(r'C:\Users\User\Desktop\Examine_unet_CAMvid\imga.png')
print(dice_coef(im,im))

Answer 1

试试这个：

from keras import backend as K
def dice_coef(y_true, y_pred):
  smooth=1
  intersection = K.sum(y_true * y_pred, axis=[1,2,3])
  union = K.sum(y_true, axis=[1,2,3]) + K.sum(y_pred, axis=[1,2,3])
  return = K.mean((2. * intersection + smooth)/(union + smooth), axis=0)