code

[Velpro-collab]

logits_m = torch.cat([logits_v, logits_i], 0).float() with torch.no_grad(): self.infraredclassifier.weight.data = self.infraredclassifier.weight.data * (1 - self.update_rate) \

• self.infrared_classifier.weight.data self.update_rate self.visibleclassifier.weight.data = self.visibleclassifier.weight.data (1 - self.update_rate) \

• self.visible_classifier.weight.data * self.update_rate

      logits_v_ = self.infrared_classifier_(feat[sub == 0])
      logits_i_ = self.visible_classifier_(feat[sub == 1])
      logits_m_ = torch.cat([logits_v_, logits_i_], 0).float()
  
  loss_id += self.ce_loss_fn(logits_m, logits_m_.softmax(dim=1)) 

  作者，你好，请问一下这部分代码在模型里有什么作用？