Skip to content

2016 ilsvrc

조회 수 12 추천 수 0 2019.08.31 21:20:32

Trimps-Soushen used the pretrained models from Inception-v3, Inception-v4, Inception-ResNet-v2, Pre-Activation ResNet-200, and Wide ResNet (WRN-68–2) for classification, and found out Top-10 difficult categories as above. Diverse results are obtained, which means there is no models being dominant for all categories. Each of the models are strong at classifying some categories, but also weak at classifying some categories. The diversity of models can be used for improving the accuracy. During training, Trimps-Soushen just performed multi-scale augmentation & large mini batch size. During testing, multi-scale + flip are used with dense fusion.

 


https://towardsdatascience.com/review-trimps-soushen-winner-in-ilsvrc-2016-image-classification-dfbc423111dd

List of Articles
번호 제목 글쓴이 날짜 조회 수
1594 MXNET SSD WHRIA 2019-09-04 10
» 2016 ilsvrc WHRIA 2019-08-31 12
1592 open new mate terminal WHRIA 2019-08-11 13
1591 mariaDB cache 설정 WHRIA 2019-08-04 79
1590 crontab 사용법 WHRIA 2019-08-04 12
1589 python with upload WHRIA 2019-07-28 248
1588 yolo custom WHRIA 2019-07-25 19
1587 stuff [2] WHRIA 2019-07-15 14
1586 batch normalization explain WHRIA 2019-07-14 45
1585 결극 senet 이 문제 WHRIA 2019-07-13 9
1584 은행은 믿을 곳이 못 되는군... WHRIA 2019-07-12 17
1583 image clip [1] WHRIA 2019-07-06 45
1582 윈도우 파일 검색 옵션 WHRIA 2019-06-14 38
1581 모든 code 를 python3 로 migration 중 WHRIA 2019-06-08 49
1580 리눅스 samba mount 정리 [1] WHRIA 2019-05-26 69

Powered by Xpress Engine / Designed by Sketchbook

sketchbook5, 스케치북5

sketchbook5, 스케치북5

나눔글꼴 설치 안내


이 PC에는 나눔글꼴이 설치되어 있지 않습니다.

이 사이트를 나눔글꼴로 보기 위해서는
나눔글꼴을 설치해야 합니다.

설치 취소