ExecutionEnviroment problem on optimizer at traininOptions

1 view (last 30 days)
I am working on Virtual Machine instace on google cloud and aiming to use gpu power for training but when I added ExecutionEnviroment, it gave me optimizer error. What can I do?
options = trainingOptions('sgdm', ...
'MiniBatchSize',75, ...
'MaxEpochs',1, ...
'InitialLearnRate',1e-4, ...
'Shuffle','every-epoch', ...
'Verbose',false, ...
'Plots','training-progress',...
'ValidationData',imdsValidation, ...
'ExecutionEnvironment','multi-gpu');
Error using nnet.cnn.TrainingOptionsSGDM (line 117)
'ExecutionEnviroment' is not an option for solver 'sgdm'.
Error in trainingOptions (line 315)
opts = nnet.cnn.TrainingOptionsSGDM(varargin{:});
Error in MachineLearning (line 29)
options = trainingOptions('sgdm', ...
  1 Comment
yanqi liu
yanqi liu on 27 Dec 2021
yes,sir,may be
'ExecutionEnvironment','auto'
to run and check the output

Sign in to comment.

Answers (1)

Joss Knight
Joss Knight on 28 Dec 2021
It looks like you typed ExecutionEnviroment instead of ExecutionEnvironment (ie. you missed the second 'n').

Community Treasure Hunt

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

Start Hunting!