search

fyu / drn

Dilated Residual Networks
https://www.vis.xyz/pub/drn
BSD 3-Clause "New" or "Revised" License
1.1k stars 219 forks source link

evaluation results(mIou) with validation dataset #20

Open wldeephi opened 6 years ago

wldeephi commented 6 years ago

hello @fyu , when I run as follows with your released pretrained model: python segment.py test -d ./dataset/cityscapes/ -c 19 --arch drn_d_105 --pretrained output/drn-d-105_ms_cityscapes.pth --phase val --batch-size 1 --ms

it gives the a lower mIou(44%) then your performance,

lxtGH commented 6 years ago

I think your batch-size is too small

d-li14 commented 5 years ago

@wldeephi Have you solved the problem? I have tried this pretrained model and got reasonable performance. @lxtGH Evaluation process doesn't need a large batch size.

lxtGH commented 5 years ago

@d-li14 Thanks, I didn't notice the evaluation process. @wldeephi Have you got the correct answer?