Conversation
ice-tong
reviewed
Oct 20, 2022
ice-tong
reviewed
Oct 20, 2022
ice-tong
reviewed
Oct 20, 2022
ice-tong
reviewed
Oct 20, 2022
Co-authored-by: yancong <32220263+ice-tong@users.noreply.github.com>
Co-authored-by: yancong <32220263+ice-tong@users.noreply.github.com>
Collaborator
Author
|
UT all passed locally |
Collaborator
Author
|
Kindly ping @RangiLyu have a look |
RangiLyu
approved these changes
Oct 21, 2022
zhouzaida
reviewed
Oct 25, 2022
zhouzaida
reviewed
Oct 25, 2022
zhouzaida
reviewed
Oct 25, 2022
zhouzaida
reviewed
Oct 25, 2022
zhouzaida
reviewed
Oct 25, 2022
zhouzaida
reviewed
Oct 25, 2022
zhouzaida
reviewed
Oct 25, 2022
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
ZwwWayne
reviewed
Oct 25, 2022
mmeval/metrics/coco_detection.py
Outdated
| iou_thrs (float | List[float], optional): IoU threshold to compute AP | ||
| and AR. If not specified, IoUs from 0.5 to 0.95 will be used. | ||
| Defaults to None. | ||
| classwise_result (bool): Whether to return the computed |
Collaborator
There was a problem hiding this comment.
Simply using classwise is fine, eval_classwise or return_classwise might also be OK.
For now, classwise_results does not provide more meaningful information than classwise.
Collaborator
Author
There was a problem hiding this comment.
Update all detection classwise_result -> classwise
Collaborator
Author
There was a problem hiding this comment.
Other metrics such as MeanIoU may also need to update
zhouzaida
approved these changes
Oct 25, 2022
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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.
Continue #9
Related PR: open-mmlab/mmdetection#9079
Before refactor:
After refactor:
Not load ann_file:
The area in coco is based on gt_mask. if using gt_bbox, it will lead to different small/medium/large AP results. Moreover, the area calculated from gt_mask area in CocoDetectionMetric is almost equal to coco-json file (still a little difference in small AP). So if only calculate bbox ap, and do not load ann_file, it is suggested to load mask at the same time.
Using gt_box area:
Using gt_mask area:
Load ann_file: