清空筛选条件
清空筛选条件

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

5 次查看（过去 30 天）
kollikonda Ashok kumar
回答： Joss Knight 2023-4-4
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);

请先登录，再回答此问题。

回答（1 个）

Joss Knight
Joss Knight 2023-4-4
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.

类别

在 Help Center 和 File Exchange 中查找有关 Get Started with MATLAB 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by