Optimization of _create_object_prediction_list_from_original_predictions for Detectron2 model. Significant speed improvement. #865
Conversation
This file contains 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
I found the function
_create_object_prediction_list_from_original_predictionsfor the Detectron2 model to be quite slow, particularly when working with large images (5400x2700).To improve performance, I have rewritten the function using list comprehension and have only moved necessary objects to the CPU, avoiding early use of tolist().
I managed to get inference time down from ~30sec/it to ~10sec/it
Performance comparison:
Before optimization
After optimization
