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

Video partition feature #3597

Open
wants to merge 4 commits into
base: master
Choose a base branch
from

Conversation

hex-plex
Copy link

@hex-plex hex-plex commented Mar 29, 2024

Overview

Closes #3596

  • Updated Build Partition Tree
  • Added Notebook for the same
  • Updated blur kernel and inpaint for video
  • Require fixing the internal plot video
  • Require to clean up a bit of code in notebook
  • Requires to have plot for both script and notebook (currently plotting available for notebook)

I am happy for others to point out any issue they see in the implementation

Checklist

  • All pre-commit checks pass.
  • Unit tests added (if fixing a bug or adding a new feature)

Copy link
Collaborator

@CloseChoice CloseChoice left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks a lot for the PR, this looks like an amazing addition to the library. I have to admit that I do not understand the code fully from taking a first glance but am keen to look into this. Since this is a new feature would you be so kind to point us to some examples we can test this on (without looking at the notebook, I would guess that's a good place to start)? We would need to have tests for this anyway and it might be a good way for us maintainers to get familiar with this feature. This is just an offer, you are also most welcome to implement the tests yourself if you wish.

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

Successfully merging this pull request may close these issues.

ENH: Partition Explainer for Video Models
2 participants