Effacer les filtres
Effacer les filtres

How to change training and plotting options when training a deep network?

13 vues (au cours des 30 derniers jours)
Fatma Diab
Fatma Diab le 11 Nov 2021
Commenté : Mohammad Sami le 22 Nov 2021
I have Matlab R2021a and I need to modify the option ‘OutputNetwork’ from the default ('last-iteration') into 'best-validation-loss' in trainingOptions by using this command:
options = trainingOptions('OutputNetwork', 'best-validation-loss');
but this option is not found in matlab R2021a. Could you please help me?

Réponses (1)

Mohammad Sami
Mohammad Sami le 12 Nov 2021
From matlab documentation, you can only use this option if you specified validation data as well.
  • 'best-validation-loss' – Return the network corresponding to the training iteration with the lowest validation loss. To use this option, you must specify 'ValidationData'.
  2 commentaires
Fatma Diab
Fatma Diab le 12 Nov 2021
Modifié(e) : Fatma Diab le 12 Nov 2021
I have validation data and my options are:
options = trainingOptions('adam', ...
'MiniBatchSize',20, ...
'MaxEpochs',10, ...
'InitialLearnRate',0.0001, ...
'Shuffle','every-epoch', ...
'ValidationData', imdsValidation, ...
'ValidationFrequency',300, ...
'OutputNetwork', 'best-validation-loss',...
'Verbose',true, ...
but this error appears:
Error using nnet.cnn.TrainingOptionsADAM (line 132)
'OutputNetwork' is not an option for solver 'adam'.
Error in trainingOptions (line 317)
opts =nnet.cnn.TrainingOptionsADAM(varargin{:});
Mohammad Sami
Mohammad Sami le 22 Nov 2021
This functionality is recently introduced in Matlab R2021b.
Network Training: Return network with lowest validation loss
When training a neural network using the trainNetwork function, output the network with the lowest validation loss by setting the OutputNetwork name-value argument of the trainingOptions function to "best-validation-loss".
You may try using checkpoint path for this perhaps. See the available options in R2020a here
CheckpointPathPath for saving checkpoint networks
character vector
Path where checkpoint networks are saved, specified as a character vector.
Data Types: char
For more on checkpoint see here

Connectez-vous pour commenter.


En savoir plus sur Image Data Workflows dans Help Center et File Exchange




Community Treasure Hunt

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

Start Hunting!

Translated by