Omniglot dataset using MLP model got shape error during training.

🐛 **Describe the bug**
A clear and concise description of what the bug is.

I tried avalanche using sample code from your GitHub and tutorials.
I tried to implement Omniglot dataset using MLP model. I am getting this error.

🐜 **To Reproduce**
Steps / minimal snipped of code to reproduce the issue.

🐝 **Expected behavior**
A clear and concise description of what you expected to happen.

🐞 **Screenshots**
If applicable, add screenshots to help explain your problem.

🦋 **Additional context**
Add any other context about the problem here like your python setup.