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 |
---|---|---|---|---|
229 | 배당세금 | WHRIA | 2015.10.14 | 111 |
228 | 인정이자 | WHRIA | 2016.01.23 | 111 |
227 | sqlite to mysql | WHRIA | 2016.10.18 | 108 |
226 | 인생무상 | WHRIA | 2016.01.18 | 106 |
225 | mcnemar | WHRIA | 2019.11.20 | 103 |
224 | . | WHRIA | 2016.10.01 | 102 |
223 | t test | WHRIA | 2019.02.13 | 102 |
222 | 윈도 10 잠금화면 없애기 [1] | WHRIA | 2015.12.25 | 101 |
221 | open new mate terminal | WHRIA | 2019.08.11 | 101 |
220 | 오랜만에 쓰다. | WHRIA | 2015.06.26 | 100 |
219 | 가끔은 시간을 돌렸으면... | WHRIA | 2016.06.09 | 100 |
218 | 서버 업그레이드 하다. [1] | WHRIA | 2016.04.29 | 99 |
217 | add extra raid disk | WHRIA | 2020.01.05 | 99 |
216 | kfda [5] | WHRIA | 2020.04.29 | 97 |
215 | 중국 스마트 폰 | WHRIA | 2014.09.29 | 96 |