Nvidia published a recent paper that detailed a system able to progressively grow the architecture of a generative adversarial network during the training phase. This network was able to produce images nearing photorealism at a faster pace than previous models, pretty exciting stuff! I’ll explain how it works both in theory and code in this video.
Published on February 24, 2018 by Carlo LepelaarsCategory AI Deep Learning Tag A.I. (Artificial Intelligence) CNN (Convolutional Neural Network) Explanation GAN (Generative Adversarial Network) NVIDIA Short Siraj Raval
October 24, 20189561 0
August 16, 20185871 0
February 22, 20188611 1