Data Augmentation not working

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.

Answer 1

[Jyothis Gireesh]

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.

https://www.mathworks.com/help/deeplearning/ref/imagedataaugmenter.html

[Hridayi]

So then how would we increase the "number" of augmentations? Is that just a matter increasing the amount of epochs that the training runs for?

[Jyothis Gireesh]

Please take a look at this link, which answers a very similar question

https://www.mathworks.com/matlabcentral/answers/365694-why-using-imagedataaugmenter-doesn-t-increase-the-size-of-my-training-data-set

Hope this helps !!

Answer 2

[Mahmoud Afifi]

Check this augmenter.

It applies color augmentation and is shown to improve the accuracy for image classification and semantic segmentation. Check the paper for more details.