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 | mariaDB cache 설정 | WHRIA | 2019.08.04 | 283 |
228 | open new mate terminal | WHRIA | 2019.08.11 | 102 |
» | 2016 ilsvrc | WHRIA | 2019.08.31 | 114 |
226 | MXNET SSD | WHRIA | 2019.09.04 | 122 |
225 | distributed training [2] | WHRIA | 2019.10.30 | 122 |
224 | python pdf writer | WHRIA | 2019.11.04 | 352 |
223 | mcnemar | WHRIA | 2019.11.20 | 105 |
222 | Micro- and macro-averages | WHRIA | 2019.11.28 | 155 |
221 | linux raid | WHRIA | 2019.11.30 | 69 |
220 | Keratinocytic Skin Cancer Detection on the Face Using Region-Based Convolutional Neural Network | WHRIA | 2019.12.07 | 374 |
219 | Basic tutorial to develop driver on windows | WHRIA | 2019.12.07 | 452 |
218 | SAS controller SAS 9212-4i | WHRIA | 2019.12.08 | 159 |
217 | raid monitor | WHRIA | 2019.12.15 | 68 |
216 | windows softraid monitor | WHRIA | 2019.12.19 | 85 |
215 | pytorch mini batch size | WHRIA | 2019.12.19 | 97 |