Error when checking target: expected dense_3 to have shape (3,) but got array with shape (1,)

Question

I am working on training a VGG16-like model in Keras, on a 3 classes subset from Places205, and encountered the following error:

ValueError: Error when chec         


        

Answer 1

The reason for this is you would have used 'binary' class_mode in the fit_generator() method for a multi class problem. Change that to 'categorical' and the error goes.