Ich bin mit einem multiple-output-Modell in keras model1 = Model(input=x, output=[y2,y3]) model1.compile((optimizer='sgd', loss=cutom_loss_function) meine custom_loss_function ist; def custom_loss(y_true, y_pred): y2_pred = y_pred[0] y2_true = y_true[0] loss = K.mean(K.square(y2_true - y2_pred), axis=-1) return loss Ich will nur zum