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Outdated suggestions cannot be applied.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.
since we set mr=4 as default while training, I do the same thing to evaluation, so the evaluation is in mr=4 level which saves cuda memory and speed up.
Also the curve of mask mAP is now closer to cocoapi. Check https://wandb.ai/laughing/evaluation-test?workspace=user-laughing.
base
is the old one, 24.1(dashboard) vs 26.7(cocoapi), which got a big jump.optimized
is the speed up version, 26.5(dashboard) vs 26.9(cocoapi).In my case, the speed tasks 1min(3.5mins before) and pycocotool evaluation tasks 10mins(18mins before) now.
Btw since I have different coco path, I got the cocoapi result manually which the dashboard didn't show it.