Data Augmentation not working
2 visualizzazioni (ultimi 30 giorni)
Mostra commenti meno recenti
Hridayi
il 14 Nov 2019
Risposto: Mahmoud Afifi
il 2 Apr 2020
Hi,
I'm trying to do data augmentation using 'ImageDataAugmenter' on a PixelLabelImageDatastore but the rate of my training is not decreasing (as it should if more images are added).
I'm not getting any error but the my training progress shows the same number of iterations and epochs as my non-augmented dataset.
This is my code:
imageAugmenter = imageDataAugmenter( ...
'RandRotation',[-10,10], ...
'RandXTranslation',[-10 10], ...
'RandYTranslation',[-10 10])
augimds = pixelLabelImageDatastore(imds,pxds,'DataAugmentation',imageAugmenter,'OutputSize',imageSize)
trainedNet_aug = trainNetwork(augimds,lgraph,options)
Does Data augmentation add new images to the datastore? Because it still shows my original 300 images in the augimds variable.
0 Commenti
Risposta accettata
Jyothis Gireesh
il 18 Nov 2019
As per the MATLAB documentation for “imageDataAugmenter”, the augmented images are not saved to memory. So, the size of “augimds” would effectively remain the same in MATLAB workspace. But these images are used while training.
You may refer to the following link on “imageDataAugmenter” for any clarifications.
2 Commenti
Jyothis Gireesh
il 19 Nov 2019
Please take a look at this link, which answers a very similar question
Hope this helps !!
Più risposte (1)
Mahmoud Afifi
il 2 Apr 2020
It applies color augmentation and is shown to improve the accuracy for image classification and semantic segmentation. Check the paper for more details.
0 Commenti
Vedere anche
Categorie
Scopri di più su Deep Learning Toolbox in Help Center e File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!