How to get deep learning layer output size?
12 views (last 30 days)
Show older comments
Itzik Ben Shabat
on 2 Apr 2019
Edited: Angelo Yeo
on 9 Feb 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
0 Comments
Accepted Answer
Maria Duarte Rosa
on 5 Apr 2019
Hi Itzik,
Have you tried analyzeNetwork?
4 Comments
Utkarsh Virtuous
on 19 Jan 2021
net.Layers().Weights give you the learned parameters. Specify the layer number in bracket.
Angelo Yeo
on 9 Feb 2024
Edited: Angelo Yeo
on 9 Feb 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.
More Answers (0)
See Also
Categories
Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!