A problem about the result

Tramac / awesome-semantic-segmentation-pytorch

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)

Apache License 2.0

2.8k stars 580 forks source link

A problem about the result #127

Open WBS-123 opened 4 years ago

WBS-123 commented 4 years ago

in the paper of fcn(Fully convolutional networks for semantic segmentation),the authors report that they can get 62.2 mIOU(fcn-8s) on VOC2012 test. But your result of fcn can not reach that level. I am confused about this, could you please explain this problem for me?

scey26 commented 3 years ago

Did you solve this problem(low performance)?