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

Starting value for image input? #3

Open
stefanklut opened this issue Apr 13, 2021 · 3 comments
Open

Starting value for image input? #3

stefanklut opened this issue Apr 13, 2021 · 3 comments

Comments

@stefanklut
Copy link

Hey there, awesome implementation. I am trying to run the code to see how it performs, however I have a quick question on the input folder structure. In the code there is a check if the input image name is 0 and a check if it is 1. Which of these values is intended as the starting value of the video folder?

@alex04072000
Copy link
Owner

Hi @stefanklut ,
The implementation uses glob to grab all pngs in a folder. So no need to worry about the indexing of the first frame I think.
By the way, we use ffmpeg to extract video into frames.
ffmpeg -i xxx.mp4 %05d.png
The first frame will be named 00001.png.

@stefanklut
Copy link
Author

Thank you, the ffmpeg info was just what I needed. However, I do think filename matters since at line 235 on run_FuSta.py there is a check if the filename is 0.

@alex04072000
Copy link
Owner

That number is related to the smoothed homography matrices and flows generate by CVPR2020CODE_yulunliu_modified. The if == 0 part can be ignored I think.

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