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

조회 수: 5 (최근 30일)
kollikonda Ashok kumar
kollikonda Ashok kumar 2023년 3월 29일
답변: Joss Knight 2023년 4월 4일
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);

이 질문에 답변하려면 로그인하십시오.

답변 (1개)

Joss Knight
Joss Knight 2023년 4월 4일
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.

카테고리

Help Center 및 File Exchange에서 Get Started with MATLAB에 대해 자세히 알아보기

태그

Community Treasure Hunt

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

Start Hunting!

Translated by