I am studying a paper named
Glow: Generative Flow with Invertible 1×1 Convolutions
when I refer to Section 2:Background: Flow-based Generative Models
,They just give a Loss Function to minimizing:enter image description here
I just don't understand what the hell is the meaning in reality?Any help will be appreciate!
question from:https://stackoverflow.com/questions/65713094/what-is-the-cost-function-of-flow-based-generative-models-in-reality