External Learning & Competitions

Kaggle·경진대회

당시 Notebook과 새 로컬 실행을 나란히 놓고 전처리, 모델과 결과가 어떻게 달라졌는지 적었습니다.

Kaggle · OUTTA Basic

[2024][Basic][P1] Sign Language Classification

28×28 grayscale sign-language image classification; the historical notebook resized inputs for VGG16

로컬 재실행: accuracy 1.0000; balanced accuracy 1.0000; macro-F1 1.0000

Kaggle · OUTTA Basic

binary text classification with BERT

로컬 재실행: accuracy 0.9896; balanced accuracy 0.9307; F1 0.8879; precision 0.9115; recall 0.8655; AP 0.9187

Kaggle · OUTTA Basic

audio classification from rhythm and spectral features

로컬 재실행: accuracy 0.8142; balanced accuracy 0.8120; macro-F1 0.8108