继承CrossEntropyLoss后，调用super之后，pred和 target的size不一样为什么不报错？

class SegmentationLosses(nn.CrossEntropyLoss):
    """2D Cross Entropy Loss with Auxilary Loss"""
    def __init__(self, se_loss=False, se_weight=0.2, nclass=-1, aux_num=2,
                 aux=False, aux_weight=0.1, weight=None,
                 ignore_index=-1):
        super(SegmentationLosses, self).__init__(weight, None, ignore_index)
        self.se_loss = se_loss
        self.aux = aux
        self.nclass = nclass
        self.se_weight = se_weight

    def forward(self, *inputs):  
            pred1, target = tuple(inputs)
            print(pred1.size())
            print(target.size())
            a =  super(SegmentationLosses, self).forward(pred1, target)
            print(a)
            return a

下面是我debeg截图，显示pred1, target这两个参数的size是不一样的，为什么没有报错呢？

最后一层维度是1的，是可以看成向量的。能正确预测