dave_user
207
edits
Changes
no edit summary
===Generative adversarial networks===
===Progressive GAN implementation===
When using proGANs to synthesize images at high resolutions, instead of attempting to train all layers of the generator and discriminator at once to generate samples at the target resolution as it is usually done, the networks are initially created with a block containing only a bunch of layers and are progressively grown to output higher resolution versions of the images by adding more and more blocks, one at a time, after completing the training of the previous one, as illustrated in the figure below.
[[File:Training progression.png|center|thumb|500x500px|ProGAN: training progression]]
This approach leads to a series of advantages:
*the incremental learning process greatly stabilizes training and reduces the chance of mode collapse, since the networks gradually learn a much simple piece of the overall problem.
*the low-to-high resolution trend forces the progressively grown networks to focus on high-level structure first and fill in the details later, resulting in an improvement of the quality of the final images
*increasing the network size gradually is more computationally efficient w.r.t. the classic approach of using all the layers from the start (fewer layers are faster to train because there are fewer parameters).
[[File:Fade-in progression.png|center|thumb|500x500px|ProGAN: growing progression of the model during training]]
