Closed kmike closed 11 years ago
Indeed, I'll fix this. @kmike, do you want push access to my repo?
@larsmans - I'm not sure what to do with that push access because I don't know where is this project heading to, and also you usually rewrite my PRs in a better way :) Not having push access rights is easier, at least now. But I could push simple fixes myself if you want - thanks for the offer!
You're a collaborator now, so you can push bugfixes. I'd like to discuss bigger changes, but don't wait for perfectionist me to fix stuff that's broken :)
What do you think about
1) using sum_loss instead of loss (currently the printed loss is a loss for some random sequence) and 2) printing iteration number at the same line as sum_loss (=> 2x less output lines)?