如何在Keras中创建自定义损失函数，每个样本都有所不同

Question

I have eg 100 samples (100 outputs). I would like to write custom loss function with a "weight" for each sample:

(target[j] - prediction[j])**2 + f(j),

Where f is a custom numeric function (eg j**2 ). How can I do this Now I am only able to create "universal" loss function (without "weights"):

def customloss(target,prediction):
   return (target - prediction)**2

The problem is I cannot get the index (j).

Answer 1

This might not be further relevant, but you can create a second network with an Input Layer. Towards that Input Layer you pass an Array that represents your weights.

Now wrap your model:

weight_layer = Input(shape=(None,dim))
m2 = Model(input=[m1.inputs,weight_layer],output=m1.outputs)

Since the output of a loss functions is also a Tensor you can add the weight_layer to your loss. eg:

def customloss(y_true,y_pred):
    return K.binary_crossentropy(y_true,y_pred) + weight_layer
m2.compile(optimizer='adam',loss=customloss,...)