-
Config file을 변경하지 않고 실험한다.
- 단, lr scheduler는 20epoch에 맞춰서 학습한다. (bs = 16 안되면 8)
- COCO, Pascal, ADE20k 에 대해서 Pretrain된 weight만 쓴다.
- Aspect ratio가 1:1인 config file만을 사용 한다.
- Backbone
- ConvNext
- SwinTransformer
- HRNet
- MAE
-
실험 결과 기록
- pretrained weight가 뭔지 명시하기
- confusion matrix 뽑아보기
- Best epoch의 validation score, Leader board 제출 score 적기
-
Notifications
You must be signed in to change notification settings - Fork 0
boostcampaitech4cv3/level2_semanticsegmentation_cv-level2-cv-08
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
level2_semanticsegmentation_cv-level3-cv-07 created by GitHub Classroom
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Python 95.0%
- Jupyter Notebook 3.9%
- Shell 0.8%
- Dockerfile 0.1%
- Batchfile 0.1%
- Makefile 0.1%