Never give up
블로그 이미지

Home

Write

Setting

About Me

  • 분류 전체보기 (61)
    • Computer vision (1)
      • Detection (1)
      • Segmentation (1)
      • Depth estimation (1)
      • Technique (0)
    • Programming (42)
      • Pytorch (2)
      • Python (4)
      • Linux (1)
      • (Dev|ML)OPS (0)
      • C++ (5)
      • 님들은 삽질하지 마세요 (18)
      • 코딩테스트 (2)
      • Why (1)
      • AI development (8)
      • DB (0)
    • 기본기 (3)
      • 딥러닝 관련 수학 (0)
      • 프로그래밍 (2)
    • 잡설 (6)
    • Data Insight (5)
no image
Yolo v1 paper architecture
Yolo v1 paper review Output → 7 x 7 x 30인 이유는 $$ grid * grid * {(x,y,w,h ,c)* bbox_{candidate} + class_{size}} $$ Localization Loss $$ \lambda_{coord} \sum_{i=0}^{S^2}\sum_{j=0}^{B} \mathbb{1}_{ij}^{obj}[(x_i - \hat{x}_i )^2 + (y_i - \hat{y_i})^2] \ \qquad \qquad \qquad \lambda_{coord} \sum_{i=0}^{S^2} \sum_{j=0}^{B}\mathbb{1}_{ij}^{obj}[(\sqrt w_i- \sqrt {\hat{w_i}})^2 + (\sqrt h_i - \sqrt {\ha..
2023.04.16
Computer vision/Detection
Prev 1 Next
uTube· Designed By ushin20

티스토리툴바