“A deep neural network making predictions on live camera input, trying to make sense of what it sees, in context of what it’s seen before. It can see only what it already knows, just like us.

“(not ‘style transfer’!)

“memo.tv/learning-to-see-you-are-what-you-see/

“Music: Diamanda Galas – ‘Gloomy Sunday’

“code based on (but more evolved version of)
github.com/memo/webcam-pix2pix-tensorflow

“model (ie training + inference) based on
github.com/affinelayer/pix2pix-tensorflow

“In turn based on
phillipi.github.io/pix2pix/
arxiv.org/abs/1611.07004

“In turn based on
arxiv.org/abs/1406.2661

“and
github.com/Newmu/dcgan_code
arxiv.org/abs/1511.06434

“In turn based on
github.com/goodfeli/adversarial
arxiv.org/abs/1406.2661

“In turn based on
people.idsia.ch/~juergen/deep-learning-overview.html