Clear Filters
Clear Filters

need help to convert to a dlnetwork

16 views (last 30 days)
Sri Kapali
Sri Kapali on 15 Sep 2023
Edited: Ben on 18 Sep 2023
I have this existing code
image = randi(255, [3,3,4]);
% create adder only network
inLayer = imageInputLayer(size(image), 'Name', 'data', 'Normalization', 'none');
addLayer = additionLayer(2, 'Name', 'add');
outLayer = regressionLayer('Name','output');
lgraph = layerGraph([inLayer, addLayer, outLayer]);
lgraph = connectLayers(lgraph, 'data', 'add/in2');
snet = assembleNetwork(lgraph);
I need to convert this to a dlnetwork and then train the dlnetwork using trainnet to replace the last regression output layer. How can I achieve the same?

Accepted Answer

Ben on 18 Sep 2023
Edited: Ben on 18 Sep 2023
The workflow for dlnetwork and trainnet would be something like the following:
image = randi(255,[3,3,4]);
% create network
net = [
% create as uninitialized so you can hook up the 2nd input to additionLayer before initializing
net = dlnetwork(net,Initialize = false);
net = connectLayers(net,"data","add/in2");
% initialize
net = initialize(net);
% train
opts = trainingOptions("adam");
% regressionLayer is not used, to specify loss you can use "mse" in trainnet

More Answers (0)




Community Treasure Hunt

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

Start Hunting!