How can we use Nadam optimizer in place of sgdm in training deep learning networks
5 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Training_Options = trainingOptions('sgdm', ...
'MiniBatchSize', 32, ...
'MaxEpochs', 50, ...
"InitialLearnRate", 1e-5, ...
'Shuffle', 'every-epoch', ...
'ValidationData', Resized_Validation_Data, ...
'ValidationFrequency', 40, ...
"ExecutionEnvironment","gpu",...
'Plots','training-progress', ...
'Verbose',false);
0 Kommentare
Antworten (1)
Joss Knight
am 4 Apr. 2023
You cannot do this using trainNetwork. You need to use a dlnetwork with a custom training loop so you can author your own update rule. Perhaps adam will work for you instead.
0 Kommentare
Siehe auch
Kategorien
Mehr zu Get Started with MATLAB finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!