MultiLabelSoftMarginLoss

pytorch.org/docs/stable/generated/torch.nn.MultiLabelSoftMarginLoss.html

multi-label일 때 torch에서 지원하는 loss가 있다.

class torch.nn.MultiLabelSoftMarginLoss(weight=None, size_average=None, reduce=None, reduction='mean')

[input]

• weight(type: Tensor) - 각 클래스의 가중치(a manual rescaling weight given to each class)
• size_average(type: bool)
  • 각 손실 요소에 대하여 평균화
  • By default, the losses are averaged over each loss element in the batch. Note that for some losses, there are multiple elements per sample. If the field size_average is set to False, the losses are instead summed for each minibatch. Ignored when reduce is False. Default: True
• reduce(type: bool) 
• reduction(type: string)  

$x$: in

$$loss(x, y) = -\frac{1}{C} (\sum_i y[i]log((1+exp(-x[i]))^{(-1)} + (1 - y[i])log(\frac{exp(-x[i])}{1+exp(-x[i])} ))$$