Max Pumperla

let's not close this until it's in dl4j _and_ keras import is enabled

@Zaxorn Thank you, much appreciated. Yeah, Go is massively complex and 10k samples are basically nothing. :D @macfergus do you have anything documented for experimental setup? I sure didn't and...

@wang869 @xhw98 all I can do is point you to the official documentation, which tells you how to do that: https://www.gnu.org/software/gnugo/gnugo_2.html#SEC13

@HaodongLi1029 can you please stop spamming various issues here? In the other issue @macfergus advised to check out the `chapter_14` branch, how about you start with that?

that's pretty strange. last time I evaluated this, I certainly ended up with 95% plus, most of the time. I mean, not that it really matters, the lesson is that...

@barrybecker4 I just changed the setup.py tf dependency to >= 1.10.1, so your 1.13.0 will now also work, given that you install from github.

@barrybecker4 yeah, it doesn't work like that. try `python setup.py develop` locally. `pip` doesn't do local.

yes, sorry about that. 2 errors it seems. we need to increase the keras version (so that applications 1.0.6 is used) and the other thing is that `gomill` is apparently...

@macfergus that... is a very good point. I completely forgot about this.

https://github.com/maxpumperla/deep_learning_and_the_game_of_go/blob/chapter_4/code/dlgo/scoring.py#L132 the result is computed there, and you can then just call `winner` on this `GameResult`