darts
darts copied to clipboard
drop_path_prob=0 or 0.3 in training ImageNet
the drop_path_prob is set as 0, but the paper said it follows "Regularized evolution for image classifier architecture search", which set 0.3.
Does it matter??
Have you tested the right hyperparameter "drop_path_prob"? I reproduce with drop_path_prob set as 0 and get a test accuray 70.8%.