GengDavid
Maybe this issue correlate with #9
Great to hear that! 😄
Thanks for your attention! Yep, the global_outputs should be reversed to match the label maps. Sorry for the mistake.
It seems that we need to fine-tune the pre-trained model again.
Hope [this](https://github.com/chenyilun95/tf-cpn/issues/32#issuecomment-394617506) would help you to understand.
Hi @mkocabas , Thanks for your interest in my implementation. There may be at least two configurations to be tested, ```ResNet-50+384x288``` and ```ResNet-101+384x288```. Which one do you prefer to test?...
If you are using ```1080ti```s, I think you can set ```batch_size``` more than 12 with 2 gpus while running ```ResNet-50+384x288``` model.
@mkocabas ```ResNet-50+384x288``` model with ```batch_size=12``` takes about 8G memory in my experiment.
@mkocabas About 25 epoch. I don't remember the exact figure.
Fine, thanks.