Python 在 keras 中制作自定义损失函数

Make a custom loss function in keras

提问by Subham Mukherjee

Hi I have been trying to make a custom loss function in keras for dice_error_coefficient. It has its implementations in tensorboardand I tried using the same function in keras with tensorflow but it keeps returning a NoneTypewhen I used model.train_on_batchor model.fitwhere as it gives proper values when used in metrics in the model. Can please someone help me out with what should i do? I have tried following libraries like Keras-FCN by ahundt where he has used custom loss functions but none of it seems to work. The target and output in the code are y_true and y_pred respectively as used in the losses.py file in keras.

嗨，我一直在尝试在 keras 中为 dice_error_coefficient 制作自定义损失函数。它有它的实现tensorboard，我尝试使用相同的功能与tensorflow keras但它一直返回NoneType当我用model.train_on_batch或model.fit其中在模型中的指标使用时，它提供正确的价值观。请有人帮我解决我该怎么办？我曾尝试关注 ahundt 的 Keras-FCN 等库，他在其中使用了自定义损失函数，但似乎都不起作用。代码中的目标和输出分别是 y_true 和 y_pred，如 keras 中的 loss.py 文件中使用的那样。

def dice_hard_coe(target, output, threshold=0.5, axis=[1,2], smooth=1e-5):
    """References
    -----------
    - `Wiki-Dice <https://en.wikipedia.org/wiki/S?rensen–Dice_coefficient>`_
    """

    output = tf.cast(output > threshold, dtype=tf.float32)
    target = tf.cast(target > threshold, dtype=tf.float32)
    inse = tf.reduce_sum(tf.multiply(output, target), axis=axis)
    l = tf.reduce_sum(output, axis=axis)
    r = tf.reduce_sum(target, axis=axis)
    hard_dice = (2. * inse + smooth) / (l + r + smooth)
    hard_dice = tf.reduce_mean(hard_dice)
    return hard_dice

回答by T. Nair

There are two steps in implementing a parameterized custom loss function in Keras. First, writing a method for the coefficient/metric. Second, writing a wrapper function to format things the way Keras needs them to be.

在 Keras 中实现参数化的自定义损失函数有两个步骤。首先，编写系数/度量的方法。其次，编写一个包装函数来按照 Keras 需要的方式格式化事物。

1. It's actually quite a bit cleaner to use the Keras backend instead of tensorflow directly for simple custom loss functions like DICE. Here's an example of the coefficient implemented that way:

   import keras.backend as K
   def dice_coef(y_true, y_pred, smooth, thresh):
       y_pred = y_pred > thresh
       y_true_f = K.flatten(y_true)
       y_pred_f = K.flatten(y_pred)
       intersection = K.sum(y_true_f * y_pred_f)
   
       return (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)
   

2. Now for the tricky part. Keras loss functions must only take (y_true, y_pred) as parameters. So we need a separate function that returns another function.

   def dice_loss(smooth, thresh):
     def dice(y_true, y_pred)
       return -dice_coef(y_true, y_pred, smooth, thresh)
     return dice
   

1. 对于像 DICE 这样的简单自定义损失函数，直接使用 Keras 后端而不是 tensorflow 实际上要干净一些。这是以这种方式实现的系数的示例：

   import keras.backend as K
   def dice_coef(y_true, y_pred, smooth, thresh):
       y_pred = y_pred > thresh
       y_true_f = K.flatten(y_true)
       y_pred_f = K.flatten(y_pred)
       intersection = K.sum(y_true_f * y_pred_f)
   
       return (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)
   

2. 现在是棘手的部分。Keras 损失函数只能以 (y_true, y_pred) 作为参数。所以我们需要一个单独的函数来返回另一个函数。

   def dice_loss(smooth, thresh):
     def dice(y_true, y_pred)
       return -dice_coef(y_true, y_pred, smooth, thresh)
     return dice
   

Finally, you can use it as follows in Keras compile.

最后，您可以在 Keras compile 中按如下方式使用它。

# build model 
model = my_model()
# get the loss function
model_dice = dice_loss(smooth=1e-5, thresh=0.5)
# compile model
model.compile(loss=model_dice)