https://github.com/open-mmlab/OpenPCDet/issues/432
- The metrics go like this. AP@ Easy , Medium , Hard (3 columns) .
- AP@0.70 means Average Precision with Intersection over Union (IoU) with threshold at 70% .
[which basically means that predictions with IoU less than 70% won't be considered as correct]. - AP_R40 means Average precision with 40 points approximation on the Precision-Recall curve.
(when you see plain 'AP' it's with 11 points).
https://towardsdatascience.com/map-mean-average-precision-might-confuse-you-5956f1bfa9e2 - IoU is calculated either in camera (2D bounding boxes), BEV (2D bounding boxes, top view), or 3D (rectangular cuboids).
- AOS : https://callmescone.tistory.com/304
'Project' 카테고리의 다른 글
Docker Deeplearning 환경 세팅 (0) | 2023.03.14 |
---|---|
Average Orientation Similarity (0) | 2023.02.24 |
[MMDetection3D] Pointpillars 학습 (0) | 2023.02.15 |
[MMDetection3D] Train을 해봅시다. feat error (0) | 2023.02.14 |
[MMDetection3D] Calib 없는 Custom 데이터로 Pointpillars 학습하기 (0) | 2023.02.14 |