skipping augmentedImageDatastore to train a net

1 view (last 30 days)
Following the example in "Train Deep Learning Network to Classify New Images",
How can I finetune my net without the augmentedImageDatastore step?
(I want to observe the performance when there arent any variations on the data)

Answers (1)

Cris LaPierre
Cris LaPierre on 20 Feb 2024
You will need to remove it from your network. Look into removeLayer
omer wagner
omer wagner on 21 Feb 2024
Could I use this on the same network (after performing the training on the Augmented), or that the layer is there in the final architecture?
no_aug_options = trainingOptions('sgdm', ...
'MiniBatchSize',miniBatchSize, ...
'MaxEpochs',6, ...
'InitialLearnRate',3e-4, ...
'Shuffle','every-epoch', ...
'ValidationData',imdsValidation, ...
'ValidationFrequency',valFrequency, ...
'Verbose',false, ...
no_aug_net = trainNetwork(imdsTrain,lgraph,no_aug_options);
Cris LaPierre
Cris LaPierre on 21 Feb 2024
The output of removeLayer is a new network. You decide when and where to use this new network.
I believe you will need to retrain your network if you modify it.
Use analyzeNetwork to view the layers of your network.

Sign in to comment.




Community Treasure Hunt

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

Start Hunting!