学习笔记：OriTripletLoss函数的解析 源码解析

1. 源代码

class OriTripletLoss(nn.Module):
    """Triplet loss with hard positive/negative mining.
    
    Reference:
    Hermans et al. In Defense of the Triplet Loss for Person Re-Identification. arXiv:1703.07737.
    Code imported from https://github.com/Cysu/open-reid/blob/master/reid/loss/triplet.py.
    
    Args:
    - margin (float): margin for triplet.
    """
    
    def __init__(self, batch_size, margin=0.3):
        super(OriTripletLoss, self).__init__()
        self.margin = margin
        self.ranking_loss = nn.MarginRankingLoss(margin=margin)

    def forward(self, inputs, targets):
        """
        Args:
        - inputs: feature matrix with shape (batch_size, feat_dim)
        - targets: ground truth labels with shape (num_classes)
        """
        n = inputs.size(0)
        
        # Compute pairwise distance, replace by the official when merged
        dist = torch.pow(inputs, 2).sum(dim=1, keepdim=True).expand(n, n)
        dist = dist + dist.t()
        dist.addmm_(1, -2, inputs, inputs.t())
        dist = dist.clamp(min=1e-12).sqrt()  # for numerical stability
        
        # For each anchor, find the hardest positive and negative
        mask = targets.expand(n, n).eq(targets.expand(n, n).t())
        dist_ap, dist_an = [], []
        for i in range(n):
            dist_ap.append(dist[i][mask[i]].max().unsqueeze(0))
            dist_an.append(dist[i][mask[i] == 0].min().unsqueeze(0))
        dist_ap = torch.cat(dist_ap)
        dist_an = torch.cat(dist_an)
        
        # Compute ranking hinge loss
        y = torch.ones_like(dist_an)
        loss = self.ranking_loss(dist_an, dist_ap, y)
        
        # compute accuracy
        correct = torch.ge(dist_an, dist_ap).sum().item()
        return loss, correct

2. 解析

应该可以理解这个函数的大概流程了。