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 |
---|---|---|---|---|
1699 | bay trail ubuntu 20.04 [1] | WHRIA | 2020.12.24 | 57 |
1698 | 32 bit UEFI [6] | WHRIA | 2020.12.24 | 208 |
1697 | sroc [1] | WHRIA | 2020.12.10 | 63 |
1696 | test | WHRIA | 2020.12.03 | 50 |
1695 | dkms for r8125 | WHRIA | 2020.11.12 | 96 |
1694 | unattended upgrade | WHRIA | 2020.11.01 | 478 |
1693 | pytorch pretrained | WHRIA | 2020.10.28 | 150 |
1692 | steamlit | WHRIA | 2020.10.15 | 212 |
1691 | sample size | WHRIA | 2020.10.13 | 4236 |
1690 | Transformer | WHRIA | 2020.10.09 | 156 |
1689 | file lock | WHRIA | 2020.09.22 | 101 |
1688 | onnx broswer | WHRIA | 2020.09.15 | 43 |
1687 | fda 인증 | WHRIA | 2020.09.03 | 213 |
1686 | ubuntu cuda nvidia-smi | WHRIA | 2020.08.29 | 867 |
1685 | concat network [3] | WHRIA | 2020.08.27 | 152 |