My question is, in particular, if these are the contents of the data set that I uploaded, and the label represents 0 top 1 bottom 2 right. I want it to do the training based on distinguishing between them. Can I do that?
Yes you can train a model to distinguish your labels. You can write out each line of your table as a file and the use the filename as the label (see this). Or you can upload your data and label within the EI Studio.