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.

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

About the ratioHard Example Mining #193

Open
mawj111 opened this issue Nov 1, 2022 · 3 comments
Open

About the ratioHard Example Mining #193

mawj111 opened this issue Nov 1, 2022 · 3 comments

Comments

@mawj111
Copy link

mawj111 commented Nov 1, 2022

No description provided.

@mawj111 mawj111 closed this as completed Nov 1, 2022
@mawj111 mawj111 reopened this Nov 1, 2022
@mawj111
Copy link
Author

mawj111 commented Nov 1, 2022

@biubug6 Hello! After reading the code, I have a question about the ratio of HEM. I see that the ratio of positive and negative samples is set to 1:3 in SSD, why do you set the ratio of positive and negative samples to 1:7? I would appreciate it if you could reply. Thank you very much.

@mawj111
Copy link
Author

mawj111 commented Nov 1, 2022

criterion = MultiBoxLoss(num_classes, 0.35, True, 0, True, 7, 0.35, False)

@mawj111
Copy link
Author

mawj111 commented Nov 1, 2022

@biubug6 Also, why set threshold to 0.35 rather than 0.5? I would appreciate it if you could reply.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant