June 14, 2018, midnight
By : Eric A. 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.
Labels: coding , machine_learning
There are no comments for this article.