You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, thanks for the good work, and for the performance in subspace. Are you run each experiment four times with 4 random seeds and select the best to report? Just as what previous work did? This part not be illustrated on paper, just wanna check if it's right.
The text was updated successfully, but these errors were encountered:
Hello. That is correct; for S1-S4 subspaces we report the best result following the original RobustDARTS, to encourage fair comparison with its baselines. (For the reference of other fellows that might check this thread later: on the original DARTS Space, we report both average and best results of running the whole search algorithms under different seeds, to establish direct comparisons with all previous methods regardless of their adopted reporting schema.)
Hi, thanks for the good work, and for the performance in subspace. Are you run each experiment four times with 4 random seeds and select the best to report? Just as what previous work did? This part not be illustrated on paper, just wanna check if it's right.
The text was updated successfully, but these errors were encountered: