-
Notifications
You must be signed in to change notification settings - Fork 27
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
hard triplet convergence #8
Comments
In theory, difficult sample mining should be useful to further improve the model effect. In my vision, it is possible to first fine-tune the pre-trained model with a normal classification loss. When the model learns to a certain bottleneck, the triple loss is used for difficult sample learning. Of course, in my actual practice, I train both losses at the same time. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I use triple loss between data of two modalities to reduce the distance between different modalities of the same class and increase the distance between different modalities of different class. But when I use batch_all loss, the valid set loss has not changed; now using hard_loss, the valid set loss still has not changed. What is the reason? I found some answers that triplet is difficult to converge. What do you do to deal with triplet loss convergence?
The text was updated successfully, but these errors were encountered: