Jason Antic

If it's something you think is useful for others, sure that'd probably be the best place. Otherwise feel free to dm me!

I’ve been having trouble getting the repeatable GAN process to run the second time. Still working on investigating. But I’ll follow later this week.

I carried over a habit from fastai notebooks which may not necessarily be great for this case which is that you have to run some cells carefully before doing the repeat. Namely- you'll need to make sure data_gen is initialized under 64px again. That part is dumb and I know it.

If I recall correctly it was that when I switched that part from 0 to 1 it wasn’t finding the 0 checkpoint it had tried to save.

Ohh that’s right. So what you need to do is look for the set of weights that work of all the checkpoints that are saved. Select it, and rename in to what you need here. This is the pain in the ass part of NoGAN at this point. Larger batch size helps a lot in stabilization.

The number at the end is the iteration.

Ah I see, that's what this is referring to? "Find the checkpoint just before where glitches start to be introduced." I thought that was referring to the same thing as "repeating the cycle below a few times (about 5-8?)" -- misunderstood! I may have to start over