mxnet
2018.05.17 11:21
senet 18.68% 4.47%
se-50 (SE-ResNeXt-50 (32 x 4d)) 20.97% 5.54%
resnext-101 (64x4d) 20.4% 5.3%
resnet-152 23% 6.7%
1070, 8GB
resnet -> batch 26 , 50img/sec
se-50 -> batch 39 , 35img/sec
resnext -> batch 16 , 25img/sec
댓글 2
| 번호 | 제목 | 글쓴이 | 날짜 | 조회 수 |
|---|---|---|---|---|
| 289 | let's encrypt 받는법 | WHRIA | 2018.01.11 | 1649 |
| 288 | reverse VNC | WHRIA | 2018.02.14 | 326 |
| 287 | kakao | WHRIA | 2018.02.25 | 141 |
| 286 | IEEE Spectrum | WHRIA | 2018.02.27 | 307 |
| 285 | security 0 | WHRIA | 2018.03.02 | 2447 |
| 284 | 당좌대월이자율 | WHRIA | 2018.03.06 | 2594 |
| 283 | intel 내장 그래픽 / CUDA | WHRIA | 2018.05.12 | 3120 |
| » | mxnet [2] | WHRIA | 2018.05.17 | 3199 |
| 281 | deep learning framework | WHRIA | 2018.05.17 | 1771 |
| 280 | skin cancer [1] | WHRIA | 2018.05.23 | 1457 |
| 279 | Interpretation of the Outputs of Deep Learning Model Trained with Skin Cancer Dataset [1] | WHRIA | 2018.06.02 | 7680 |
| 278 |
달러 환율
 | WHRIA | 2018.06.16 | 1267 |
| 277 | letencrypt - win | WHRIA | 2018.08.12 | 36 |
| 276 | 나이 40에... | WHRIA | 2018.09.01 | 134 |
| 275 | faster rcnn resnet 101 | WHRIA | 2018.09.09 | 169 |
resnet은 32 , se-50 은 56, resnext 는 26 을 batch 로 줄 수 있고 성능은 2배정도 - 1080ti