DACON
search Subscribe
noti 0

    MY XP

    XP Info

    LEVEL 1

    Until Next Level 150 XP

    0/150 XP

    Today's XP

    0 / 800

    Total XP

    0

    Earned XP

    0

    Spent XP

    0

    Sign in with your SNS accounts

    google
    Sign in with Google
    Don't have an account? Sign Up
    Verify your email

    To sign up, you must verify your email. Do you want to resend the code?
    [Dacon] sign up verification

    Your email must be verified to complete the sign up process. Please verify your email below to complete.

    Terms of Use

    Privacy policy

    Consent to receive marketing information

    DACON Monthly the 2nd Computer Vision Learning Competition

    Algorithm | CV | Classification | Control | Accuracy

    • moneyIcon Prize : 540만원
    • 45 Users Completed
    Closed
    Overview Data Code (share) Talk Leaderboard

     

    Private 8위, efficientNet 모델 앙상블, threshold 전처리 기법 활용

    제로콜라호호
    2022.10.06 01:46 540 Views language
    comments 0

    기존 모델 학습에서 epoch를 더 늘렸습니다.

    새로운 dataset을 만들어서( original 사진 33333개 + threshold 처리 33333개로 60000개 데이터) 학습한 모델 추가.  
    추가한 모델과 기존 모델 epoch늘려서 앙상블 했습니다.

    Code
    0 Comments
    Login Required
    0 / 1000
    📣 The comment input field has been moved to the top of the comment list!
    to_list List
    Previous
    [Private 7위, Efficientnet Ensemble + TTA]
    Competition - [광운대] 컴퓨터 비전 AI 경진대회
    Likes 3
    Views 904
    Comments 0
    3년 전
    Current
    Private 8위, efficientNet 모델 앙상블, threshold 전처리 기법 활용
    Competition - [광운대] 컴퓨터 비전 AI 경진대회
    Likes 2
    Views 540
    Comments 0
    3년 전
    Next
    최종 Private 1위 코드 공유 (public lb: 0.9003, private 0.9018)
    Competition - [광운대] 컴퓨터 비전 AI 경진대회
    Likes 14
    Views 834
    Comments 0
    3년 전