Deep Network Designer Toolbox

Hi, I am trying to train a simple network using the Deep Network Designer Toolbox.

Please how do I go about debbugging the error message below without exporting to code from deep network designer?

'augmentedImageDatastore cannot form MiniBatches of data because input image sizes differ in 3rd dimension. Consider using 'ColorPreprocessing' option to ensure all augmented images have same number of channels.'

Thank you.

Answer 1

[Srivardhan Gadila]

As the error clearly states, it seems that your data contains a mixture of grayscale and RGB images, use ColorPreprocessing Name-Value pair argument to ensure that all output images have the same number of channels as required by the imageInputLayer of your network.

Refer to the description of ColorPreprocessing of AugmentedImageDatastore and Import Data into Deep Network Designer for more information.