How can we use Nadam optimizer in place of sgdm in training deep learning networks

4 views (last 30 days)
kollikonda Ashok kumar
kollikonda Ashok kumar on 29 Mar 2023
Answered: Joss Knight on 4 Apr 2023
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);

Sign in to answer this question.

Answers (1)

Joss Knight
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.

Categories

Find more on Get Started with MATLAB in Help Center and File Exchange

Tags

Community Treasure Hunt

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

Start Hunting!