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

The question about eval result #29

Closed
Yanchunswallow opened this issue Mar 2, 2018 · 2 comments
Closed

The question about eval result #29

Yanchunswallow opened this issue Mar 2, 2018 · 2 comments

Comments

@Yanchunswallow
Copy link

Hi Zheng:
I have read your work carefully.
I attempt to evaluate the test result to 210 test videos base on your demo code, but the result is different to yours:

 |  0.1  | 0.2   |  0.3  |  0.4  |  0.5 |
 |47.7  | 43.5 | 36.3 | 28.7 | 19.0|

my test results used your evaluation code.

 |  0.1  | 0.2   |  0.3  |  0.4  |  0.5 |
 | 26.3 | 26.7 | 24.6 | 22.9 | 18.9|

I don't know why there is such a big different?
Thanks in advance!

@zhengshou
Copy link
Owner

Thank you for your interest in our work. Some people have reproduced the results. Maybe you can check your data preparation or S-CNN usage in detail.

@Yanchunswallow
Copy link
Author

@zhengshou Thank you for your reply!
BTW, could you please release or send me the trained model of MEXaction2 dataset? My email is [email protected]. Thanks very much!

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

2 participants