This is a checkpoint of a set of long tests with reduced-complexity networks. Some takeaways:
1) A full GAN using the resnet discriminator does appear to converge, but the quality is capped.
2) Likewise, a combination GAN/feature loss does not converge. The feature loss is optimized but
the model appears unable to fight the discriminator, so the G-loss steadily increases.
Going forwards, I want to try some bigger models. In particular, I want to change the generator
to increase complexity and capacity. I also want to add skip connections between the
disc and generator.
After doing some thinking and reading on the subject, it occurred to me that
I was treating the generator like a discriminator by focusing the network
complexity at the feature levels. It makes far more sense to process each conv
level equally for the generator, hence the FlatProcessorNet in this commit. This
network borrows some of the residual pass-through logic from RRDB which makes
the gradient path exceptionally short for pretty much all model parameters and
can be trained in O1 optimization mode without overflows again.
The receptive field of the original was *really* low. This new one has a
receptive field of 36x36px patches. It also has some gradient issues
that need to be worked out
This bad boy is for a workflow where you train a model on disjoint image sets to
downsample a "good" set of images like a "bad" set of images looks. You then
use that downsampler to generate a training set of paired images for supersampling.
