How can we use Nadam optimizer in place of sgdm in training deep learning networks
4 views (last 30 days)
Show older comments
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 Comments
Answers (1)
Joss Knight
on 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 Comments
See Also
Categories
Find more on Get Started with MATLAB 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!