Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Question about loss function during segmentation #98

Open
LW130003 opened this issue Jan 6, 2021 · 1 comment
Open

Question about loss function during segmentation #98

LW130003 opened this issue Jan 6, 2021 · 1 comment

Comments

@LW130003
Copy link

LW130003 commented Jan 6, 2021

Hi Xu-Ji,

Currently, I have modified the Segmentation Script to train another dataset. Both the dataset loader B and A are the same but I noticed the avg loss returned (between head B and A) have large margin of difference:
image

Any idea why this happened? Am I training it correctly

Thank you and regards
@xu-ji
Copy link
Owner

xu-ji commented Jan 21, 2021

If they have different numbers of clusters, the losses for the two heads will likely be different, so I do not think it is cause for concern.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@xu-ji @LW130003