Loss function

[zhangfc7]

Hi, how can I use more than one loss function?

[scaomath]

The simplest way is to write your own:

def loss1(pred, target):
    '''first loss here'''
    return ...

def loss2(pred, target):
    '''second loss here'''
    return ...

def loss(pred, target):
    return a*loss1(pred, target) + b*loss2(pred, target)

or something like this, more advanced loss can be implemented through torch's _WeightedLoss class template.