You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, you can try python main.py --train --dataset cityscapes --exp lr1e-2_crop769_batch20_lastmult10 --epochs 480 --base_lr 0.01 --crop_size 769 --batch_size 20 --last_mult 10, which should get >76 mIOU, which is ~1 lower than what is reported in the paper, unfortunately. I was using 4 GPUs, so batch size 5 on each GPU.
Hi, you can try python main.py --train --dataset cityscapes --exp lr1e-2_crop769_batch20_lastmult10 --epochs 480 --base_lr 0.01 --crop_size 769 --batch_size 20 --last_mult 10, which should get >76 mIOU, which is ~1 lower than what is reported in the paper, unfortunately. I was using 4 GPUs, so batch size 5 on each GPU.
Hi, thx for your reply. How about the experiment with WS in Cityscapes?
Hi, I saw the segmentation results are mainly in Pascal VOC, anyone tried it on Cityscapes?
The text was updated successfully, but these errors were encountered: