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

question about Normalize #120

Closed
Feynman1999 opened this issue Jul 25, 2020 · 4 comments
Closed

question about Normalize #120

Feynman1999 opened this issue Jul 25, 2020 · 4 comments

Comments

@Feynman1999
Copy link

Feynman1999 commented Jul 25, 2020

in /mmedit/datasets/pipelines/normalization.py, Normalize class , call function, why we need the line 40?
image

@hejm37
Copy link
Collaborator

hejm37 commented Jul 25, 2020

Hi, those lines (L39-L44) are added to support video data format. For example, in video super-resolution data pipeline, results['lq'] is a list of video frames.

@Feynman1999
Copy link
Author

Hi, those lines (L39-L44) are added to support video data format. For example, in video super-resolution data pipeline, results['lq'] is a list of video frames.

yes, I know that, But why need two for loop, L40 and L43

@hejm37
Copy link
Collaborator

hejm37 commented Jul 25, 2020

I see, the outer for loop is not necessary and will be removed. Thanks for your feedback!

@Feynman1999
Copy link
Author

Thanks to the mean and std are 0 and 1 for video task😅

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