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

Mean and std for normalization? #4

Closed
SunDoge opened this issue Oct 17, 2020 · 2 comments
Closed

Mean and std for normalization? #4

SunDoge opened this issue Oct 17, 2020 · 2 comments

Comments

@SunDoge
Copy link

SunDoge commented Oct 17, 2020

Thanks for your implementation!
Would you mind sharing your mean and std for video normalization for training process? In main.py you use 0.5, is it the same in training?

@kylemin
Copy link
Owner

kylemin commented Oct 18, 2020

Hi,
Thank you for your interest.
Yes, following the I3D convention, pixel values are rescaled to [-1, 1] in both training and testing, so you can just use the transform function.

@SunDoge
Copy link
Author

SunDoge commented Oct 18, 2020

I see. Thx.

This issue was closed.
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