Effacer les filtres
Effacer les filtres

Custom Layer Learnable Parameters Initialization.

2 vues (au cours des 30 derniers jours)
David Ernesto Caro
David Ernesto Caro le 8 Mar 2020
I created a Custom Layer with Learnable Parameters (https://www.mathworks.com/help/deeplearning/ug/define-custom-deep-learning-layer.html)
However, to initialize these parameters I need to know the outputsize of the previous layer. I noticed that some pre-defined layers such as FullyConnected automaticly initialize its own weights using information from previous layers. Is there a way to automatize the weights initialization on custom layers at network initialization?
  1 commentaire
Jose Cortes-Briones
Jose Cortes-Briones le 9 Sep 2020
I asked a similar question a while ago and never got a response :/

Connectez-vous pour commenter.

Réponse acceptée

Joss Knight
Joss Knight le 16 Jan 2023

Plus de réponses (1)

John Smith
John Smith le 4 Oct 2021
Unfortunately, at least as of version 2021a, Matlab doesn't provide staright forward capabilities to automatically initialize learnable parameters of a custom layer similar to its built-in layers.
There's a workaround though using a shadow built-in network nested inside your custom layer (see here). Matlab will automatically initialize this layer from which learnable parameters you can pick up the values that you need.
It's a kludge, but it works (I've implemented such a scheme myself.


En savoir plus sur Image Data Workflows dans Help Center et File Exchange




Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by