How to get deep learning layer output size?

33 visualizaciones (últimos 30 días)
Itzik Ben Shabat
Itzik Ben Shabat el 2 de Abr. de 2019
Editada: Angelo Yeo el 9 de Feb. de 2024
Hi,
I am getting to know MATLAB's capability with deep learning (I am fluent in TensorFlow).
I built a very big computation graph.
My question is :
How can I get a specific layer's output sizes without training the network? (for dubugging purposes)
I know that I can do:
features = activations(net,X,layer)
but this requires me to train the network (I want to avoid it since it will take a while).
Thanks

Respuesta aceptada

Maria Duarte Rosa
Maria Duarte Rosa el 5 de Abr. de 2019
  4 comentarios
Utkarsh Virtuous
Utkarsh Virtuous el 19 de En. de 2021
net.Layers().Weights give you the learned parameters. Specify the layer number in bracket.
Angelo Yeo
Angelo Yeo el 9 de Feb. de 2024
Editada: Angelo Yeo el 9 de Feb. de 2024
@Mirko Prezioso: A new class NetworkAnalysis will be added from R2024a. This class can be retrieved as an output of analyzeNetwork function, and will capture the output of analyzeNetwork. This will include a property called "LayerInfo" as a table.

Iniciar sesión para comentar.

Más respuestas (0)

Etiquetas

Productos


Versión

R2019a

Community Treasure Hunt

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

Start Hunting!

Translated by