Multi-class Classification

[davidcocc]

Hi everyone!
I'm trying to train a multi-class classification model using the classical pipeline (as soon as I finish, I'm looking forward to test the quantum one, too!), but I've encountered some problems which made me feel stuck.
Basically, when passing train_dataset and val_dataset to trainer.fit, , I get "Provided arrays must be of equal shape. Got arrays of shape torch.Size([30, 2]) and torch.Size([30, 8])."
I am using CrossEntropyLoss as loss function, and I have to say I'm kinda new to this stuff, so I'm afraid I missed some step which lead me to these issues.
Could some one help me to figure out what is happening?
Thank you in advance.

[dimkart]

Hi, this error means that the array with your predicted values has not the same shape with the array of your target values. The rows (second number) of both arrays need to be the same and to correspond to the number of the classes in your dataset (for the classical case).