Theodore Galanos
Theodore Galanos
Would you be releasing training code for the original models? Would be nice to try some on v3s (if possible).
Bumping this, wonder if it's coming soon. Seems like an exciting approach!
> > > Love the artistic direction of this thread. My interest (other than reading the answer to @htoyryla's question), is in the tooling on top of this beautiful technology...
Nice job @enricoros ! This is a great start. I wonder can we use generated images as seeds for another generation with deep sleep? or that is too constrictive? Interactive...
> > > @enricoros I'm all ears :) Just let me know how you would envision the API and I'll put in some time later this week! this might sound...
Would you be willing to share your setup, for training this on a custom dataset? I'm trying to go through this myself, only started, and would welcome some advice.
Nevermind, it was actually quite easy to do!
I think this indeed might be not having scotch. When you change the number of processors in other methods you usually need to change the coefficients for xyz as well....
Both simple and hierarchical methods require coefficients to work correctly. The coefficients (C) are nothing else than the number of splits per dimension (x y z). The only real requirement...