-
It would help to separate modeling from inference if we allowed model transformations from discrete to relaxed discrete.
One way to accomplish this would be via a poutine, or more specifically via …
-
## Abstract
- propose Vector Quantised Variational AutoEncoder (VQ-VAE)
- generative model that learns discrete representations
- prior is learnt rather than static
- solves the issue of "po…
-
Thank you for the great work!
I tried to repoduce `VQGAN OpenImages (f=8), 8192, GumbelQuantization` model based on the config file from the cloud. (the detailed config file is in below.)
VQGA…
-
1. For DARTS complexity analysis, anyone have any idea how to derive the *(k+1)\*k/2* expression ? Why 2 input nodes ? How will the calculated value change if graph isomorphism is considered ? Why …
-
-
The PixelDrawer currently has no support for limiting the colors - it only support full three channel RGB. It would be preferable to be able to limit the colorspace to either subsets of RGB or to a fi…
-
Hello @noveens,
Thank you for your excellent work and patience response before! I'm confused about the distilled dataset saved in './results/distilled_data' seems to contain continuous variables not …
-
Are there plans to introduce differentiable samples?
Thanks!
-
Hi, thanks for fabulous work!
### Questions about Training:
- According to the [G_optimizer_reuse](https://github.com/shallowdream204/SODA-SR/blob/main/options/swinir/train_soda_sr_classical.json#…
-