Threaded inference #1203
Merged
Threaded inference #1203
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Codecov Report
@@ Coverage Diff @@
## develop #1203 +/- ##
===========================================
- Coverage 72.00% 71.91% -0.10%
===========================================
Files 132 132
Lines 23328 23403 +75
===========================================
+ Hits 16798 16830 +32
- Misses 6530 6573 +43
📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
roomrys
approved these changes
Mar 1, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Basic threaded inference implementation. With this change, SLEAP object construction (and tracking) happen in a separate thread than neural network inference. This should unblock the GPU while we're building
PredictedInstances.Quick tests show that this super simple implementation increases overall inference speed by ~20% in cases where there are many instances/tracks.
It's not pretty, but I think we'll need to wait to de-duplicate the logic until we refactor the inference module into submodules or something.
Types of changes
Does this address any currently open issues?
[list open issues here]
Outside contributors checklist
Thank you for contributing to SLEAP!
❤️