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

조회 수: 11(최근 30일)
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?


Mohammad Sami
Mohammad Sami 2021년 11월 12일
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'.
  댓글 수: 2
Mohammad Sami
Mohammad Sami 2021년 11월 22일
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

댓글을 달려면 로그인하십시오.





Community Treasure Hunt

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

Start Hunting!

Translated by