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

add yolov8 mask support, improve mask processing speed by 4-5x #1039

Merged
merged 7 commits into from
Jun 2, 2024

Conversation

mayrajeo
Copy link
Contributor

Cleaner version of #888 . Adds support for instance segmentation with yolov8 and makes slicing instance segmentation results use COCO-style annotations. Haven't yet tested with oriented bounding boxes.

Known shortcomings:

  • NMS/NMM/GREEDYNMM is still done with bounding boxes instead of polygons
  • Not a problem of sahi, but yolov8 models can output multipart polygons even though yolov8 annotation format doesn't support those.

@mayrajeo mayrajeo changed the title cleaner edits cleaner edits of #888 May 20, 2024
sahi/utils/cv.py Outdated Show resolved Hide resolved
sahi/utils/cv.py Outdated Show resolved Hide resolved
sahi/slicing.py Outdated Show resolved Hide resolved
sahi/predict.py Outdated Show resolved Hide resolved
@fcakyon
Copy link
Collaborator

fcakyon commented May 20, 2024

Amazing job @mayrajeo 🚀

@fcakyon fcakyon changed the title cleaner edits of #888 add yolov8 mask support, improve mask processing speed by 4-5x May 20, 2024
@fcakyon fcakyon added this pull request to the merge queue Jun 2, 2024
Merged via the queue into obss:main with commit 0191fbb Jun 2, 2024
9 checks passed
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.

2 participants