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

모델 save/load 기능 추가 #2

Closed
kuro11pow2 opened this issue Sep 9, 2021 · 1 comment
Closed

모델 save/load 기능 추가 #2

kuro11pow2 opened this issue Sep 9, 2021 · 1 comment
Labels
enhancement New feature or request

Comments

@kuro11pow2
Copy link
Owner

kuro11pow2 commented Sep 9, 2021

학습된 net의 state_dict을 저장하고 불러올 수 있어야 함.
모델을 통째로 저장하는 건 의존성이 너무 커서 부적절한 방법임.

https://tutorials.pytorch.kr/recipes/recipes/saving_and_loading_models_for_inference.html

음 일단 runner에 추가하고 run에서 _episode_loop를 _train_loop로 바꾸고 _play_loop를 추가해야 할 것 같음.

아니다 _episode_loop는 놔두고 _episode_prepare에서 저장한 모델을 불러오는 함수를 호출하는 게 나을 듯.
_episode_sim 을 train_sim과 play_sim으로 분리해서 학습 하지 않는 분기를 만들자

@kuro11pow2 kuro11pow2 added the enhancement New feature or request label Sep 9, 2021
@kuro11pow2 kuro11pow2 changed the title 모델 저장 기능 추가 모델 save/load 기능 추가 Sep 13, 2021
@kuro11pow2
Copy link
Owner Author

아니다 그냥 episode_sim에서 put_data하고 train_net만 멈추게 하는 게 나을 듯

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

1 participant