yifenggithub

损失函数形参的维度不一致

3

请问我运行您的代码出现了错误 RuntimeError: margin_ranking_loss : All input tensors should have same dimension but got sizes: input1: torch.Size([1024, 3]), input2: torch.Size([1024, 3]), target: torch.Size([1]) ，我查阅了方法的源码形参要求维度都保持一致，但是您模型里面调用方法的维度好像是不一致的 y = torch.Tensor([1]).to(self.device) loss = self.loss_func(p_score, n_score,...