Some puzzled questions about details in realizing triplet loss

[swg209]

  # 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

你好，在损失函数的实现部分，TripletLoss(nn.Module)里面的上述代码我不太理解，能麻烦你解读一下吗？ 非常非常感谢。

[lqili]

@swg209 https://www.cnblogs.com/kk17/p/10252440.html