Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[FEAT] Pickle, Train 및 Inference 코드 수정 #20

Open
3 tasks
Eddie-JUB opened this issue Jan 28, 2024 · 0 comments
Open
3 tasks

[FEAT] Pickle, Train 및 Inference 코드 수정 #20

Eddie-JUB opened this issue Jan 28, 2024 · 0 comments

Comments

@Eddie-JUB
Copy link
Contributor

Background

  1. code/to_pickle.py
  • 조건에 따른 pkl 파일 관리 필요
  1. code/train.py
  • 생성된 pkl 파일 폴더별로 네이밍 필요
  • 이에 따른 wandb 네이밍 필요
  • pin_memory 설정 필요
  1. code/inferece.py
  • 기존 코드 inference 시 best.pth가 아닌 lasteset.pth 로 설정되는 부분 수정 필요

To do

  • code/to_pickle.py 수정: pkl 파일 생성 조건에 따라 폴더 생성
  • code/train.py 수정: pkl 폴더생성, wandb 네이밍, pin_memory 설정, cuda device 설정 및 ETA 추가
  • code/inferece.py 수정: best 없을 시 lastest.pth로 inference
Eddie-JUB added a commit that referenced this issue Jan 29, 2024
* feat: k_fold split

#7

* feat: for train and valid

#10

* fix: deteval, train

#10

* feat: train with pickle data

#14

* fix: path issue in to_pickle file

#14

* chore: update train_val to json_name

#10

* chore: change arg name

#14

* feat: normalize, custom_augmentation

#16

* feat: custom augmentation

#16

* feat: modify to_pickle.py, train.py, inference.py codes

#20

* chore: update code

#16

---------

Co-authored-by: Eddie-JUB <bjonguk@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant