So this is “in the works”, I haven’t succeeded yet. The ultimate goal is to be able to upscale a shitty 70kb jpeg to a megapixel jpeg using trained neural networks. Badass, rite? Well, the disclaimer here is that I’ve been chipping away at this project and haven’t yet got a functioning setup. So without further ado, here’s my fucking trainwreck.
I started off following the guide at alexjc/neural-enhance. My first attempt involved me thinking I was slick and I could just grab the docker container since it’s already installed, configured, and the neural networks trained with more than a few already very usable targets.