Is it possible to train the rstar model using early stopping method?

[gooners1886]

I'm learning the theory and code of the rstar.
But I find the number of iterations is hard to determine. Is the code support testing on validation set after training several epochs?

[gkioxari]

You should test snapshots on the validation set with the test code. It is fast to test the validation set. I didn't use the validation set at all, since I report results in it and that would make it unfair. I trained it enough epochs though (Thus, results could be improved even more with a better stopping criterion than my self-imposed one)