14. Juni 2018 00:00
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.
Etiketten: coding , machine_learning
Zu diesem Artikel gibt es keine Kommentare.