jeudi 14 juin 2018 à 09:21
DeConvolution ArtifactsPar Eric Antoine Scuccimarra
If you have ever used deconvolutions to upsample layers of convnets you have probably seen artifacts and possibly checkerboard patterns. This article explains why and gives some useful tips as to how to avoid the problem. I have implemented some of the suggestions and, while it's a bit early to evaluate their efficacity, so far they seem to be helping.
Libellés: coding, machine_learning