Giters

XiaLiPKU / EMANet

The code for Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV'2019 Oral)

Home Page:https://xialipku.github.io/publication/expectation-maximization-attention-networks-for-semantic-segmentation/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Fail to reproduce your results on COCO-STUFF

zenght opened this issue · comments

commented

Hi @XiaLiPKU ! Your work is amazing, and i am appreciate that you have released your code.
May i ask question? Based on your code, i have modified your code to suit COCO-STUFF training. But i can only get 34.55% miou. I just followed your default setting, but in single gpu. ( pretrained ResNet-101, batch size 3, 30k iterations and so on...).

Looking forward to your reply!
Best wishes

commented

Hi @XiaLiPKU ! Your work is amazing, and i am appreciate that you have released your code.
May i ask question? Based on your code, i have modified your code to suit COCO-STUFF training. But i can only get 34.55% miou. I just followed your default setting, but in single gpu. ( pretrained ResNet-101, batch size 3, 30k iterations and so on...).

Looking forward to your reply!
Best wishes

Batch size is one of the most factor of segmentation's performance. In my experiment, the batch size is 16