search

Mu-ING / Person-ReID-Triplet-Loss-Model-based-on-Tensorflow

Implementation of basic triplet loss, triplet hard loss and triplet semi-hard loss
0 stars 0 forks source link

hard triplet loss #1

Open ffredd opened 1 year ago

ffredd commented 1 year ago

"Then we could choose postive with highest similairty, if positive exists, and negative with lowest similarity for each anchor" Is this statement contrary? Shouldn't it be to find the positive pair with the smallest similarity and the negative pair with the largest similarity?

ffredd commented 1 year ago

and can u provide ur email?

Mu-AIZIP commented 1 year ago

U are right and thanks for your comment! The most similar triplet should be found. U can find me with this email qing@aizip.ai

ffredd commented 1 year ago

when I use hard-triplet-loss to train the model, it's difficult to converge~ Even though the loss of my training set is decreasing, the loss of my validation set is almost unchanged. Have you ever had such a problem? How did you solve it?