The input images for activations must be of size equal to or greater than [224 224 3].
7 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
aitali hassna
el 5 de Abr. de 2020
Editada: Sai Bhargav Avula
el 11 de Abr. de 2020
my code is:
augmentedTrainset=augmentedImageDatastore(imagesize,...
trainset,'ColorPreprocessing','rgb2gray');
augmentedTestset=augmentedImageDatastore(imagesize,...
testset,'ColorPreprocessing','rgb2gray');
featureLayer = 'fc1000';
trainingFeatures = activations(net, augmentedTrainset, featureLayer, ...
'MiniBatchSize', 39, 'OutputAs', 'columns');
[224 224 3] image size
And I take an error as "The input images for activations must be of size equal to or greater than [224 224 3]."
Why I'm taking this error, how can I fix it?
2 comentarios
Geoff Hayes
el 5 de Abr. de 2020
aitali - does your test set contain any images that are smaller than 224x224x3?
Respuesta aceptada
Sai Bhargav Avula
el 8 de Abr. de 2020
Editada: Sai Bhargav Avula
el 11 de Abr. de 2020
Hi,
Is your image [224 224 3] or of different order?
And try the below code once
augmentedTrainset=augmentedImageDatastore(imagesize,...
trainset);
augmentedTestset=augmentedImageDatastore(imagesize,...
testset);
featureLayer = 'fc1000';
trainingFeatures = activations(net, augmentedTrainset, featureLayer, ...
'MiniBatchSize', 39, 'OutputAs', 'columns');
6 comentarios
Sai Bhargav Avula
el 11 de Abr. de 2020
The ColorPreprocessing name value can be removed. As all the images already has 3 channels no processing occurs.
Más respuestas (0)
Ver también
Categorías
Más información sobre Convert Image Type 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!