Contrastive Confusion

[jlian2]

   ` ## loss functions
    if self.loss_func == 'contrastive':
        nloss       = torch.mean(torch.cat([torch.pow(pos_dist, 2),torch.pow(F.relu(self.margin - neg_dist), 2)],dim=0))
    elif self.loss_func == 'triplet':
        nloss   = torch.mean(F.relu(torch.pow(pos_dist, 2) - torch.pow(neg_dist, 2) + self.margin))

    scores = -1 * torch.cat([pos_dist,neg_dist],dim=0).detach().cpu().numpy()

    errors = tuneThresholdfromScore(scores, labelnp, []);

    return nloss, errors[1]

` Why there are three inputs for contrastive ?

[joonson]

The code deals with positive and negative pairs at once because of the batch formation, but does not compare positives to negatives unlike the triplet loss. Let me know if you see any problem with the implementation.