Categorizing training/testing set in the back end

[Rexmiao]

Future versions are intended to not have the user cognisant of training/testing sets, and this will be handled automatically. for development + debugging, it was needed. Additionally, there is some research that needs to be done here to determine how best to optimally separate the patches into training/validation, so we opted to do "nothing" (full manual) for the time being for simplicity