Nguyen Viet Tuan

In theory, if the model can work well on short text recognition, it also recognizes text at good accuracy by separating your sequence. I think you should use window sliding...

> https://github.com/clovaai/stargan-v2/issues/103#issuecomment-911051743 do you know why having an error when training on multiple GPUs?

learning rate was set to 1 and it don't change during training process

but it affect to optimizer

Hi, Could you tell me how to build from your source on mac ? Thanks

I also have slow

hi bupticybee is that ok to save json 3 rounds for short deck

> > hi bupticybee is that ok to save json 3 rounds for short deck > > Yeah that's okay for sure, but it would become very slow. I look...

yeah I understanded that is what I confuse when I implement your code in river round in real time. I calculate that if we solve (turn + river) for 1755...

btw could u tell me what is isomorphism