Custom Layer Learnable Parameters Initialization.

3 ビュー (過去 30 日間)
David Ernesto Caro
David Ernesto Caro 2020 年 3 月 8 日
Hi!
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?
David
  1 件のコメント
Jose Cortes-Briones
Jose Cortes-Briones 2020 年 9 月 9 日
I asked a similar question a while ago and never got a response :/

サインインしてコメントする。

回答 (1 件)

John Smith
John Smith 2021 年 10 月 4 日
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.
  1 件のコメント
Jose Cortes-Briones
Jose Cortes-Briones 2021 年 10 月 4 日
Thanks!

サインインしてコメントする。

タグ

製品


リリース

R2018a

Community Treasure Hunt

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

Start Hunting!

Translated by