keras combining two losses with adjustable weights

Question

So here is the detail description. I have a keras functional model with two layers with outputs x1 and x2.

x1 = Dense(1,activation=\'relu\')(prev_in         


        

Answer 1

It seems that propagating the "same loss" into both branches will not take effect, unless alpha is dependent on both branches. If alpha is not variable depending on both branches, then part of the loss will be just constant to one branch.

So, in this case, just compile the model with the two losses separate and add the weights to the compile method:

model.compile(optmizer='someOptimizer',loss=[loss1,loss2],loss_weights=[alpha,1-alpha])

Compile again when you need alpha to change.

---

But if indeed alpha is dependent on both branches, then you need to concatenate the results and calculate alpha's value:

singleOut = Concatenate()([x1,x2])

And a custom loss function:

def weightedLoss(yTrue,yPred):
    x1True = yTrue[0]
    x2True = yTrue[1:]

    x1Pred = yPred[0]
    x2Pred = yPred[1:]

    #calculate alpha somehow with keras backend functions

    return (alpha*(someLoss(x1True,x1Pred)) + ((1-alpha)*(someLoss(x2True,x2Pred))

Compile with this function:

model.compile(loss=weightedLoss, optimizer=....)