TF/KERAS：将列表作为单个输出的损失传递

Question

我的模型只有一个输出，但我想结合两个不同的损失函数，（注意：类数 = 24 ）。

c = 0.8
lamda = 32

# My personalized loss function
def selective_loss(y_true, y_pred): .
    loss = K.categorical_crossentropy(
        K.repeat_elements(y_pred[:, -1:], CLASSES, axis=1) * y_true[:, :-1],
        y_pred[:, :-1]) + lamda * K.maximum(-K.mean(y_pred[:, -1]) + c, 0) ** 2
    return loss

p = np.ones(CLASSES) / CLASSES#The weights of class.

#And doing de model compile.
model.compile(loss = ['categorical_crossentropy', selective_loss],
              loss_weights = p,
              optimizer= sgd,                            
              metrics = ['accuracy'])

但它抱怨我需要两个输出，因为我定义了两个损失：

ValueError: When passing a list as loss, it should have one entry per model outputs. The model has 1 outputs, but you passed loss=['categorical_crossentropy', <function selective_loss at 0x7fcfb68daa60>]

您是否必须将两种损失合二为一？ 如果是这样，你会怎么做？

还是最好有两个输出？ 这会影响预测吗？ 会怎样？

Answer 1

我在两个损失函数之间进行加权，使用 alpha 0.5 但其他浮点数也有效：

#Private loss is the selective_loss.
def total_loss(y_true, y_pred):
    alpha = 0.5
    return (1-alpha)*categorical_crossentropy(y_true, y_pred) + alpha*selective_loss(y_true, y_pred)

#Compile the model with weighting loss.
model.compile(loss = total_loss,
              loss_weights = p,
              optimizer= sgd,                            
              metrics = ['accuracy'])