2016 ilsvrc
2019.08.31 21:20
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.
댓글 0
번호 | 제목 | 글쓴이 | 날짜 | 조회 수 |
---|---|---|---|---|
1641 | mysql 암호화 [2] | WHRIA | 2020.04.24 | 45 |
1640 | php 세션 로그인 | WHRIA | 2020.04.24 | 57 |
1639 | image encryption [1] | WHRIA | 2020.04.24 | 66 |
1638 | zerohq encryption [5] | WHRIA | 2020.04.23 | 44 |
1637 | 의료영상분석장치 분류 코드 | WHRIA | 2020.04.22 | 35 |
1636 | 회귀분석 종류 | WHRIA | 2020.04.14 | 39 |
1635 | fcitx | WHRIA | 2020.04.05 | 32 |
1634 | chatbot | WHRIA | 2020.04.03 | 34 |
1633 | kernel load | WHRIA | 2020.04.03 | 33 |
1632 | plum | WHRIA | 2020.04.03 | 38 |
1631 | zmq async client server [1] | WHRIA | 2020.03.12 | 62 |
1630 | CIDR 표기법 [1] | WHRIA | 2020.03.12 | 45 |
1629 | multiple NIC ubuntu [6] | WHRIA | 2020.03.10 | 43 |
1628 | calendar javascript dropdown | WHRIA | 2020.03.01 | 36 |
1627 | sql replication 성공 [1] | WHRIA | 2020.02.20 | 40 |