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 | 1657 |
288 | reverse VNC | WHRIA | 2018.02.14 | 346 |
287 | kakao | WHRIA | 2018.02.25 | 151 |
286 | IEEE Spectrum | WHRIA | 2018.02.27 | 334 |
285 | security 0 | WHRIA | 2018.03.02 | 2464 |
284 | 당좌대월이자율 | WHRIA | 2018.03.06 | 2600 |
283 | intel 내장 그래픽 / CUDA | WHRIA | 2018.05.12 | 3152 |
» | mxnet [2] | WHRIA | 2018.05.17 | 3211 |
281 | deep learning framework | WHRIA | 2018.05.17 | 1788 |
280 | skin cancer [1] | WHRIA | 2018.05.23 | 1468 |
279 | Interpretation of the Outputs of Deep Learning Model Trained with Skin Cancer Dataset [1] | WHRIA | 2018.06.02 | 7706 |
278 |
달러 환율
![]() | WHRIA | 2018.06.16 | 1291 |
277 | letencrypt - win | WHRIA | 2018.08.12 | 46 |
276 | 나이 40에... | WHRIA | 2018.09.01 | 138 |
275 | faster rcnn resnet 101 | WHRIA | 2018.09.09 | 171 |
resnet은 32 , se-50 은 56, resnext 는 26 을 batch 로 줄 수 있고 성능은 2배정도 - 1080ti