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

Can't reproduce the result #3

Open
justopit opened this issue Dec 15, 2021 · 2 comments
Open

Can't reproduce the result #3

justopit opened this issue Dec 15, 2021 · 2 comments

Comments

@justopit
Copy link

Following your instructions, I ran the experiment on SYSU-MM01 and found it was only 56 of Rank-1 in All-Search, while your paper is 61

@northeast1st1bing
Copy link

yes ,its same to me. my Rank-1 result is between 55.8 to 53 on SYSU-MM01 in all-search and 44.5 to 42 in single search.

@ThomasjonLi
Copy link

ThomasjonLi commented Mar 15, 2022

I find this problem too.If i use the model trained by our gpu(with author's code, 120epoch),rank-1 in sysu is 52.6%(all-single); but if use the author's model, the result turns to be 62%

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

3 participants