This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
add aligned roi introduced in Detectron2 #16619
Merged
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
Kh4L
reviewed
Oct 25, 2019
|
|
||
| // Force malformed ROIs to be 1x1 | ||
| T roi_width = max(roi_end_w - roi_start_w, (T)1.); | ||
| T roi_height = max(roi_end_h - roi_start_h, (T)1.); | ||
| if (!continuous_coordinate) { // backward compatiblity |
There was a problem hiding this comment.
Why we don't also CHECK_GT here?
There was a problem hiding this comment.
save computation. pytorch doesn't do it so I just copied it.
Kh4L
approved these changes
Oct 29, 2019
wkcn
approved these changes
Oct 29, 2019
|
LGTM. Thanks |
|
Hi @Jerryzcn , could you please add an unittest? Thank you! |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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
(Brief description on what this PR is about)
add aligned ROIAlign introduced in pytorch/pytorch#23706
improved MaskRCNN mask acc by 0.2~0.3 mAP. However when training with large batch size, warmup needs to be increased.