Machine vision - neural networks - image filtering



I came across this recent work by Gene Kogan:

that is based on this code

which is based on this paper:

It takes two images and manipulates one of them to be in the “style” of the other. ("…demonstrating a method for restyling images using convolutional neural networks")

Still looking through and trying to interpret what they’ve used to define content vs style. Tried installing Lua and running it but wasn’t able to get there from here.

Does anyone have experience with anything like this? Or programming in Lua?



I’ve used Lua a tad with the NodeMCU firmware for the ESP8266 . Here is a pretty great resource for learning Lua quickly if you are already comfortable with programming. I found it to be a very simple scripting language not unlike JavaScript.