When running train.py, why can't I get the same high accuracy as in train_search.py?

[liqier]

Thanks for your work!
One question I hope can be answered: for the same data set and parameter settings, I run train.py with the best cell obtained by train_search.py. Why can't I get the same high accuracy as in train_search.py?
Look forward to your reply.

[serser]

@liqier Are you referring to the supernet performance (train_search) vs. subnet performance (best cell)? Supernet is a tool for us to find the best cell (what we care), we shall not expect the two have the exact same accuracy.