The input images for activations must be of size equal to or greater than [224 224 3].
3 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
aitali hassna
am 5 Apr. 2020
Bearbeitet: Sai Bhargav Avula
am 11 Apr. 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 Kommentare
Geoff Hayes
am 5 Apr. 2020
aitali - does your test set contain any images that are smaller than 224x224x3?
Akzeptierte Antwort
Sai Bhargav Avula
am 8 Apr. 2020
Bearbeitet: Sai Bhargav Avula
am 11 Apr. 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 Kommentare
Sai Bhargav Avula
am 11 Apr. 2020
The ColorPreprocessing name value can be removed. As all the images already has 3 channels no processing occurs.
Weitere Antworten (0)
Siehe auch
Kategorien
Mehr zu Convert Image Type finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!