Custom Layer Learnable Parameters Initialization.

3 views (last 30 days)
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

Accepted Answer

Joss Knight
Joss Knight on 16 Jan 2023

More Answers (1)

John Smith
John Smith on 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.

Products


Release

R2018a

Community Treasure Hunt

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

Start Hunting!