Keras categorical_crossentropy Grouping Issue

I am working on a convolution neural network for Dogs Cats, Lizards and I have two variables / numpy arrays ( I want this to run as a categorical_crossentropy) 1. ImagePixels 2. ImageGrouping But when I run this line in jupyter notebook [login to view URL](ImagePixels, ImageGrouping, batch_size=32, epochs=100, validation_split=0.2) I get the following error ValueError: A target array with shape (21356, 3) was passed for an output of shape (None, 1) while using as loss `categorical_crossentropy`. This loss expects targets to have the same shape as the output I dont quite understand this error I have already run this line from [login to view URL] import np_utils ImageGrouping=np_utils.to_categorical(ImageGrouping) Witch I thought would have gotten the data into the format wanted.