Model swapout is a feature where, at specified intervals,
a random D and G model will be swapped in place for the
one being trained. After a short period of time, this model
is swapped back out. This is intended to increase training
diversity.
This network is just a fixed (pre-trained) generator
that performs a corruption transformation that the
generator-in-training is expected to undo alongside
SR.
It now injects noise directly into the input filters, rather than a
pure noise filter. The pure noise filter was producing really
poor results (and I'm honestly not quite sure why).
Implements a ResGenv2 architecture which slightly increases the complexity
of the final output layer but causes it to be shared across all skip outputs.
It's been a tough day figuring out WTH is going on with my discriminators.
It appears the raw FixUp discriminator can get into an "defective" state where
they stop trying to learn and just predict as close to "0" D_fake and D_real as
possible. In this state they provide no feedback to the generator and never
recover. Adding batch norm back in seems to fix this so it must be some sort
of parameterization error.. Should look into fixing this in the future.
I want to be able to specify many different transformations onto
the target data; the model should handle them all. Do this by
allowing multiple LQ paths to be selected and the dataset class
selects one at random.
This is a simpler resnet-based generator which performs mutations
on an input interspersed with interpolate-upsampling. It is a two
part generator:
1) A component that "fixes" LQ images with a long string of resnet
blocks. This component is intended to remove compression artifacts
and other noise from a LQ image.
2) A component that can double the image size. The idea is that this
component be trained so that it can work at most reasonable
resolutions, such that it can be repeatedly applied to itself to
perform multiple upsamples.
The motivation here is to simplify what is being done inside of RRDB.
I don't believe the complexity inside of that network is justified.
Add RRDBNetXL, which performs processing at multiple image sizes.
Add DiscResnet_passthrough, which allows passthrough of image at different sizes for discrimination.
Adjust the rest of the repo to allow generators that return more than just a single image.
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
