Micro- and macro-averages
2019.11.28 23:15
Micro- and macro-averages (for whatever metric) will compute slightly different things, and thus their interpretation differs. A macro-average will compute the metric independently for each class and then take the average (hence treating all classes equally), whereas a micro-average will aggregate the contributions of all classes to compute the average metric.
댓글 0
번호 | 제목 | 글쓴이 | 날짜 | 조회 수 |
---|---|---|---|---|
1564 | LG 글로벌 | WHRIA | 2019.01.31 | 68 |
1563 | ubuntu tweak | WHRIA | 2019.01.29 | 560 |
1562 | xrdp ubuntu 18.04 mate startwm.sh | WHRIA | 2019.01.29 | 957 |
1561 | resilio sync 유저로 실행 [1] | WHRIA | 2019.01.28 | 1893 |
1560 | Swap file add | WHRIA | 2019.01.02 | 2132 |
1559 | center % crop | WHRIA | 2018.12.27 | 70 |
1558 | imbalanced dataset | WHRIA | 2018.12.26 | 44 |
1557 | CNN Models | WHRIA | 2018.12.23 | 353 |
1556 | fatal error: turbojpeg.h: No such file or directory | WHRIA | 2018.11.24 | 645 |
1555 | ac-68u dd-wrt 에서 정펌으로 복구 | WHRIA | 2018.11.22 | 547 |
1554 | excel 에서 소수점 표시 함수 | WHRIA | 2018.11.08 | 199 |
1553 | mixed precision training [1] | WHRIA | 2018.11.06 | 1779 |
1552 | delayed network drive connect | WHRIA | 2018.10.07 | 152 |
1551 | faster rcnn cuda 10 | WHRIA | 2018.10.06 | 2107 |
1550 | Intro | WHRIA | 2018.10.01 | 4081 |