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.

Sign up for GitHub

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

Jump to bottom

Imbalanced Data Problem #4

Open
DongHyun99 opened this issue Sep 15, 2021 · 1 comment
Open

Imbalanced Data Problem #4

DongHyun99 opened this issue Sep 15, 2021 · 1 comment
Assignees
@DongHyun99
Labels
🐈 Change train Code 🐏 기능 구현 🐖 Augmentation

Comments

@DongHyun99
Copy link
Owner

개요

Imbalanced Data Problem

idea

나이 분포를 보면 데이터가 불균형하여 학습이 잘 이뤄지지 않을 수 있음
따라서 RandAugment를 하지 않고 오프라인으로 각 나이에 대한 Augmentation을 하여 나이에 대한 데이터의 균형을 맞춰준다.

location

bone_data/DataLoad.py
@DongHyun99 DongHyun99 self-assigned this Sep 15, 2021
@DongHyun99
Copy link
Owner Author

~57: 779장
~114: 3500장
~171: 7129장
~228: 1203장

  1. 각각 6000장으로 맞추고 (데이터를 늘릴때 그냥 복제만) 학습시에 Augmentation을 주기
  2. 3000, 3500, 7129, 1203 으로 Augmentation을 주기
  3. 각각 다양하게 Augmentation을 줘서 데이터를 크게 불린다음 학습때마다 각 분포마다 같은 사진만큼 임의로 선택해서 학습시키기

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@DongHyun99 DongHyun99

Labels
🐈 Change train Code 🐏 기능 구현 🐖 Augmentation
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@DongHyun99