Image to be categorized specifically

Thank you. help has been appreciated

Answer 1

[Rohit]

Hi Tathva,

I understand that you want to train a neural network for your dataset but are facing an error related to “ImageDataStore” having no labels.

The reason for error is that you are passing (numTrainFiles = 2) and that results in "imdsTrain" having all images and "imdsValidation" being empty.

As per the documentation, “splitEachLabel(imds,p)” splits the image files in imds into two new datastores, "imds1" and "imds2". The new datastore "imds1" contains the first p files from each label and "imds2" contains the remaining files from each label.

So all files are assigned to "imdsTrain" and there are no labels in "imdsValidation".

For your dataset you can set the parameter "numTrainFiles" to 1 if you want to split in train and validation. Otherwise, you can try to increase the number of observations in your dataset.

You can refer to the documentation link for "splitEachLabel" for further reference: https://in.mathworks.com/help/matlab/ref/matlab.io.datastore.imagedatastore.spliteachlabel.html