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

Videodataset design - redesign #23

Open
johndpope opened this issue Nov 5, 2024 · 0 comments
Open

Videodataset design - redesign #23

johndpope opened this issue Nov 5, 2024 · 0 comments

Comments

@johndpope
Copy link
Owner

Emodataset
This loads my video with sequence of frames
The length of dataset is how many videos in folder
Frames are extracted then feed into trainer

PROS

  • straightforward

CONS

  • the eager pre fetching can spiral out of control
  • I add some bandaid with while clause in get item
  • it wants to pause and get all the items up front
  • So training can’t start until all videos processed
  • I have folder with 35,000 mp4s from celebhq
  • Doesn’t work

Frame pairs
Lmdb
https://github.com/neeek2303/EMOPortraits

I attempt to rewire things - need to have another crack tomorrow

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

1 participant