Is there a way to visualize augmented image data created by imageDataAugmenter()?

Illustration
katto_went - 2021-07-08T10:24:28+00:00
Question: Is there a way to visualize augmented image data created by imageDataAugmenter()?

I would like to confirm a few images just to understand what imageDataAugmenter does. Is there a way to visualize the augmented image data created by the imageDataAugmenter?  

Related Questions

  • Is there a way to visualize augmented image data created by imageDataAugmenter()?

    • Expert Answer

    Profile picture of Kshitij Singh Kshitij Singh answered . 2025-11-20

    For R2018a.
     
    In R2018a, the ‘augmentedImageSource’ has been replaced by ‘augmentedImageDatastore’ and the ‘preview’ method can be used to preview the data as follows:
    augimds = augmentedImageDatastore(…)
ims = augimds.preview();
montage(ims{1:6,1}) % to visualize 6 images
    'preview' does not reset the datastore.
     
    In alternative, the method ‘read’ can be used to view the next batch of data as shown below:
    augimds = augmentedImageDatastore(…);
numBatches = ceil(augimds.NumObservations / augimds.MiniBatchSize);
for i = 1:numBatches
    ims = augimds.read();
    montage(ims{:,1});
    pause;
end
augimds.reset();
    ____________________________________________________________________________________________________________________
    For R2017b:
     
    The built-in functionality to do this is not available on Neural Network Toolbox (R2017b).
     
    1) One of the possible workarounds is to make use of augmentedImageSource's hidden methods and properties for iterating over the data. For example:
     
    [XTrain,YTrain] = digitTrain4DArrayData;
imageAugmenter = imageDataAugmenter('RandRotation',[-180 180],'RandXReflection',true,'RandYReflection',true);
imageSize = [28 28 1];
datasource = augmentedImageSource(imageSize,XTrain,YTrain,'DataAugmentation',imageAugmenter);
datasource.MiniBatchSize = 16;
datasource.reset();
numBatches = ceil(datasource.NumberOfObservations / datasource.MiniBatchSize);

for i = 1:numBatches
    ims = datasource.nextBatch();
    montage( cat(4, ims) );
    pause;
end
    This will show a 4x4 montage of augmented data. You can cycle through all the data by pressing any key on the keybord.
     
    2) Another workaround is to set a breakpoint on line 484 of imageDataAugmenter and then visualize variable "B" by using imshow().
     
    3) A third way would be to create a new layer just for image visualization. This layer could be placed after the imageInputLayer and all it would do is display the input images (again using 'montage' for example) during training. You would only need to edit the 'predict' method with the code to display the incoming images (X).


    Not satisfied with the answer ?? ASK NOW

    Get a Free Consultation or a Sample Assignment Review!

    Upload Assignment Talk to Expert