Skip to content

2016 ilsvrc

조회 수 22 추천 수 0 2019.08.31 22:20:32

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
1602 SAS controller SAS 9212-4i WHRIA 2019-12-08  
1601 Basic tutorial to develop driver on windows WHRIA 2019-12-07  
1600 Keratinocytic Skin Cancer Detection on the Face Using Region-Based Convolutional Neural Network WHRIA 2019-12-07 51
1599 linux raid WHRIA 2019-11-30 8
1598 Micro- and macro-averages WHRIA 2019-11-29 6
1597 mcnemar WHRIA 2019-11-20 10
1596 python pdf writer WHRIA 2019-11-04 8
1595 distributed training [2] WHRIA 2019-10-30 12
1594 MXNET SSD WHRIA 2019-09-04 21
» 2016 ilsvrc WHRIA 2019-08-31 22
1592 open new mate terminal WHRIA 2019-08-11 30
1591 mariaDB cache 설정 WHRIA 2019-08-04 157
1590 crontab 사용법 WHRIA 2019-08-04 24
1589 python with upload WHRIA 2019-07-28 257
1588 yolo custom WHRIA 2019-07-25 59

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