- Image Data Store.
- Data Store.
- Table.
- Cell array of X and Y, where X represents data while Y represents corresponding labels.
What is the correct syntax for using an augmentedImageDatastore as validation data in trainingOptions for the trainNetwork() function?
3 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Dominic Maguire
el 12 de Mayo de 2020
Comentada: Dominic Maguire
el 15 de Mayo de 2020
I have the following image datastore:
myDataset = imageDatastore('C:\MyData',...
'IncludeSubfolders',true,...
'FileExtensions','.png',...
'LabelSource','foldernames');
[imdsTrain, imdsVal, imdsTest] = splitEachLabel(myDataset, 0.6, 0.2, 'randomized');
Which I then prepare to input into some pre-trained networks:
augimdsTrain = augmentedImageDatastore([227 227 3],imdsTrain,...
'ColorPreprocessing', 'gray2rgb',...
'DataAugmentation', augmenter);
augimdsVal = augmentedImageDatastore([227 227 3],imdsVal, ...
'ColorPreprocessing', 'gray2rgb');
augimdsTest = augmentedImageDatastore([227 227 3],imdsTest,...
'ColorPreprocessing', 'gray2rgb');
What is the correct syntax for using augimdsVal as 'ValidationData'in trainingOptions? Do I just use the augmented datastore as is (as I've seen in some of the documentation):
options = trainingOptions('sgdm','InitialLearnRate', 0.0001, 'ValidationData', augimdsVal);
Or can I add labels like so:
options = trainingOptions('sgdm','InitialLearnRate', 0.0001, 'ValidationData', {augimdsVal imdsVal.Labels});
Or is there a better way?
0 comentarios
Respuesta aceptada
Harsha Priya Daggubati
el 15 de Mayo de 2020
Hi,
The name-value pair 'ValidationData' can support only the following types as a value:
So, I guess it is invalid to give labels again as a value.
Refer to the following link:
Hope this clarifies your concern!
3 comentarios
Harsha Priya Daggubati
el 15 de Mayo de 2020
As the imagedataStore has labels, there is no need to explicitly specify labels to augmented image datastore, when we use imds as the argument during creation.
Más respuestas (0)
Ver también
Categorías
Más información sobre Image Data Workflows en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!