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

Further optimizations for 3d segmentation #466

Open
constantinpape opened this issue Mar 19, 2024 · 1 comment
Open

Further optimizations for 3d segmentation #466

constantinpape opened this issue Mar 19, 2024 · 1 comment

Comments

@constantinpape
Copy link
Contributor

There are a few possible further (efficiency optimization) for the 3d segmentation:

  • Parallelize the 3d segmentation over slices if the full amg state is precomputed
  • Parallelize the closing precomputation
  • Refactor the amg state handling so that it can also be used in the standalone 3d segmentation function.

Grep Further optimization to find the locations in the code.

@constantinpape
Copy link
Contributor Author

  • Parallelize the operations for postprocessing of instance segmentation with decoder -> make sure to enable passing n_threads so that we avoid oversubscription in case of outer parallelization.

(Not strictly related to the 3d post-processing, but would be very useful for tiling based instance segmentation)

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